Daily Papers

Many machine learning systems have access to multiple sources of evidence for the same prediction target, yet these sources often differ in reliability and informativeness across inputs. In bioacoustic classification, species identity may be inferred both from the acoustic signal and from spatiotemporal context such as location and season; while Bayesian inference motivates multiplicative evidence combination, in practice we typically only have access to discriminative predictors rather than calibrated generative models. We introduce Fusion under INdependent Conditional Hypotheses (FINCH), an adaptive log-linear evidence fusion framework that integrates a pre-trained audio classifier with a structured spatiotemporal predictor. FINCH learns a per-sample gating function that estimates the reliability of contextual information from uncertainty and informativeness statistics. The resulting fusion family contains the audio-only classifier as a special case and explicitly bounds the influence of contextual evidence, yielding a risk-contained hypothesis class with an interpretable audio-only fallback. Across benchmarks, FINCH consistently outperforms fixed-weight fusion and audio-only baselines, improving robustness and error trade-offs even when contextual information is weak in isolation. We achieve state-of-the-art performance on CBI and competitive or improved performance on several subsets of BirdSet using a lightweight, interpretable, evidence-based approach. Code is available: \href{https://anonymous.4open.science/r/birdnoise-85CD/README.md{anonymous-repository}}

Robust understanding of user input is a core requirement for voice assistants deployed in real-world environments. In practice, these systems encounter heterogeneous fallback situations caused by noisy audio input, transcription errors, ambiguous requests, incomplete utterances, or unintended activations. Existing systems typically respond with generic fallback messages, which do not resolve the underlying interaction failure and can degrade user experience. We study fallback handling in a deployed smartwatch-based voice assistant for general health support in everyday environments. Our analysis is based on six months of real-world usage data from more than 500 users, yielding a dataset of 3,030 anonymized, naturally occurring fallback-triggering utterances. We contribute (1) an operational taxonomy and the annotated VoxFallbacks dataset of these interactions, (2) a comparative evaluation of different models within a classification pipeline under practical deployment constraints, and (3) practical lessons for designing robust and cost-efficient fallback mechanisms. Results show that lightweight embedding-based classifiers outperform larger generative models on most classification tasks while requiring substantially fewer computational resources.

This paper introduces FALL-E, a foley synthesis system and its training/inference strategies. The FALL-E model employs a cascaded approach comprising low-resolution spectrogram generation, spectrogram super-resolution, and a vocoder. We trained every sound-related model from scratch using our extensive datasets, and utilized a pre-trained language model. We conditioned the model with dataset-specific texts, enabling it to learn sound quality and recording environment based on text input. Moreover, we leveraged external language models to improve text descriptions of our datasets and performed prompt engineering for quality, coherence, and diversity. FALL-E was evaluated by an objective measure as well as listening tests in the DCASE 2023 challenge Task 7. The submission achieved the second place on average, while achieving the best score for diversity, second place for audio quality, and third place for class fitness.

Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate acoustic information, rather than verifying the audio stream. This issue appears across both state-of-the-art open-source omni models and leading closed-source models from providers such as Google and OpenAI. We characterize this failure mode as an audio-visual Clever Hans effect, in which models appear (falsely) audio-grounded, but actually exploit visual-acoustic correlations without verifying whether the audio and visual streams are truly aligned. To systematically study this behavior, we introduce Thud, an intervention-driven probing framework based on three counterfactual audio edits: Shift, which tests temporal synchronization; Mute, which tests sound existence; and Swap, which tests audio-visual consistency. Beyond diagnosis, we further study a two-stage alignment recipe: intervention-derived preference pairs teach audio verification, while event-level general video preferences regularize the model against over-specialization. Our best 10K-sample recipe improves average performance across the three intervention dimensions by 28 percentage points, while slightly improving performance on general video and audio-visual QA benchmarks.

We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio. Although audio-only dereverberation is a well-studied problem, our approach incorporates the complementary visual modality to perform audio dereverberation. Given an image of the environment where the reverberated sound signal has been recorded, AdVerb employs a novel geometry-aware cross-modal transformer architecture that captures scene geometry and audio-visual cross-modal relationship to generate a complex ideal ratio mask, which, when applied to the reverberant audio predicts the clean sound. The effectiveness of our method is demonstrated through extensive quantitative and qualitative evaluations. Our approach significantly outperforms traditional audio-only and audio-visual baselines on three downstream tasks: speech enhancement, speech recognition, and speaker verification, with relative improvements in the range of 18% - 82% on the LibriSpeech test-clean set. We also achieve highly satisfactory RT60 error scores on the AVSpeech dataset.

We present a joint audio-visual model for isolating a single speech signal from a mixture of sounds such as other speakers and background noise. Solving this task using only audio as input is extremely challenging and does not provide an association of the separated speech signals with speakers in the video. In this paper, we present a deep network-based model that incorporates both visual and auditory signals to solve this task. The visual features are used to "focus" the audio on desired speakers in a scene and to improve the speech separation quality. To train our joint audio-visual model, we introduce AVSpeech, a new dataset comprised of thousands of hours of video segments from the Web. We demonstrate the applicability of our method to classic speech separation tasks, as well as real-world scenarios involving heated interviews, noisy bars, and screaming children, only requiring the user to specify the face of the person in the video whose speech they want to isolate. Our method shows clear advantage over state-of-the-art audio-only speech separation in cases of mixed speech. In addition, our model, which is speaker-independent (trained once, applicable to any speaker), produces better results than recent audio-visual speech separation methods that are speaker-dependent (require training a separate model for each speaker of interest).

From professional filmmaking to user-generated content, creators and consumers have long recognized that the power of video depends on the harmonious integration of what we hear (the video's audio track) with what we see (the video's image sequence). Current approaches to video generation either ignore sound to focus on general-purpose but silent image sequence generation or address both visual and audio elements but focus on restricted application domains such as re-dubbing. We introduce Mirage, an audio-to-video foundation model that excels at generating realistic, expressive output imagery from scratch given an audio input. When integrated with existing methods for speech synthesis (text-to-speech, or TTS), Mirage results in compelling multimodal video. When trained on audio-video footage of people talking (A-roll) and conditioned on audio containing speech, Mirage generates video of people delivering a believable interpretation of the performance implicit in input audio. Our central technical contribution is a unified method for training self-attention-based audio-to-video generation models, either from scratch or given existing weights. This methodology allows Mirage to retain generality as an approach to audio-to-video generation while producing outputs of superior subjective quality to methods that incorporate audio-specific architectures or loss components specific to people, speech, or details of how images or audio are captured. We encourage readers to watch and listen to the results of Mirage for themselves (see paper and comments for links).

Diffusion models power a vast majority of text-to-audio (TTA) generation methods. Unfortunately, these models suffer from slow inference speed due to iterative queries to the underlying denoising network, thus unsuitable for scenarios with inference time or computational constraints. This work modifies the recently proposed consistency distillation framework to train TTA models that require only a single neural network query. In addition to incorporating classifier-free guidance into the distillation process, we leverage the availability of generated audio during distillation training to fine-tune the consistency TTA model with novel loss functions in the audio space, such as the CLAP score. Our objective and subjective evaluation results on the AudioCaps dataset show that consistency models retain diffusion models' high generation quality and diversity while reducing the number of queries by a factor of 400.

Video-to-audio (V2A) generation aims to synthesize realistic audio that is both semantically consistent with and temporally synchronized to a silent video. Despite recent progress, many methods still rely on multi-stage training, resulting in high computational costs and long runtimes, or transform visual input into text to leverage pretrained text-to-audio models, sacrificing fine-grained temporal cues. To overcome these limitations, we propose Flowley, an end-to-end, single-stage training architecture that produces soundtracks by combining visual features with textual prompts. Crucially, we introduce Progressive Soft-masked Cross-Attention, which embeds audio-visual synchronization directly within its attention mechanism, adding zero additional computational cost compared to standard attention layers. We further observe that existing V2A benchmarks lack sound-oriented descriptive captions, which can potentially degrade the quality of the synthesized audio. To remedy this, we propose SoundCap, a plug-and-play pipeline for creating detailed, sound-aware captions that guide the model. Remarkably, without integrating any pretrained audio-visual alignment modules, Flowley achieves state-of-the-art performance on VGGSound across multiple metrics. Moreover, by incorporating SoundCap, we further exceed the performance of the strongest existing close-sourced methods in terms of audio quality in the zero-shot setting.

Video dubbing is a cornerstone of multimedia content creation, aiming to synthesize synchronized acoustic sequences for visual streams. While Text-to-Speech (TTS) and Text-to-Audio (TTA) generation have each achieved remarkable progress, existing dubbing systems remain confined to isolated speech synthesis without incorporating sound effects and ambient audio, forcing practitioners to rely on fragmented workflows and laborious manual post-mixing. To address this limitation, we present HoliDubber, a holistic video dubbing framework that moves beyond speech-only generation by enabling the joint synthesis of speech and sound effects from a single text prompt. Specifically, HoliDubber adopts a patch-based autoregressive diffusion transformer architecture, where a causal language model autoregressively models aggregated patch embeddings to capture global temporal structure, and a Diffusion Transformer decoder generates high-fidelity continuous tokens within each patch, following a divide-and-conquer strategy. To achieve cross-modal alignment, visual features are encoded into patch-level representations and fused with audio patches via cross-attention, enabling the model to ground speech generation in the speaker's visual articulation dynamics. In addition, we introduce HoliDub-Bench, a benchmark curated from established datasets with synchronized video-text-audio triplets designed for holistic dubbing evaluation. Extensive experiments demonstrate that HoliDubber significantly outperforms existing methods across multiple benchmarks in speech quality, synchronization, and speaker similarity. Furthermore, results on HoliDub-Bench validate the effectiveness of joint speech-and-sound generation, establishing a new paradigm for holistic video dubbing in complex acoustic scenes. The demo page of the project is https://holidubber.github.io

Audio chaptering, the task of automatically segmenting long-form audio into coherent sections, is increasingly important for navigating podcasts, lectures, and videos. Despite its relevance, research remains limited and text-based, leaving key questions unresolved about leveraging audio information, handling ASR errors, and transcript-free evaluation. We address these gaps through three contributions: (1) a systematic comparison between text-based models with acoustic features, a novel audio-only architecture (AudioSeg) operating on learned audio representations, and multimodal LLMs; (2) empirical analysis of factors affecting performance, including transcript quality, acoustic features, duration, and speaker composition; and (3) formalized evaluation protocols contrasting transcript-dependent text-space protocols with transcript-invariant time-space protocols. Our experiments on YTSeg reveal that AudioSeg substantially outperforms text-based approaches, pauses provide the largest acoustic gains, and MLLMs remain limited by context length and weak instruction following, yet MLLMs are promising on shorter audio.

We present MGAudio, a novel flow-based framework for open-domain video-to-audio generation, which introduces model-guided dual-role alignment as a central design principle. Unlike prior approaches that rely on classifier-based or classifier-free guidance, MGAudio enables the generative model to guide itself through a dedicated training objective designed for video-conditioned audio generation. The framework integrates three main components: (1) a scalable flow-based Transformer model, (2) a dual-role alignment mechanism where the audio-visual encoder serves both as a conditioning module and as a feature aligner to improve generation quality, and (3) a model-guided objective that enhances cross-modal coherence and audio realism. MGAudio achieves state-of-the-art performance on VGGSound, reducing FAD to 0.40, substantially surpassing the best classifier-free guidance baselines, and consistently outperforms existing methods across FD, IS, and alignment metrics. It also generalizes well to the challenging UnAV-100 benchmark. These results highlight model-guided dual-role alignment as a powerful and scalable paradigm for conditional video-to-audio generation. Code is available at: https://github.com/pantheon5100/mgaudio

Existing video-to-audio (V2A) generation methods predominantly rely on text prompts alongside visual information to synthesize audio. However, two critical bottlenecks persist: semantic granularity gaps in training data, such as conflating acoustically distinct sounds under coarse labels, and textual ambiguity in describing micro-acoustic features. These bottlenecks make it difficult to perform fine-grained sound synthesis using text-controlled modes. To address these limitations, we propose AC-Foley, an audio-conditioned V2A model that directly leverages reference audio to achieve precise and fine-grained control over generated sounds. This approach enables fine-grained sound synthesis, timbre transfer, zero-shot sound generation, and improved audio quality. By directly conditioning on audio signals, our approach bypasses the semantic ambiguities of text descriptions while enabling precise manipulation of acoustic attributes. Empirically, AC-Foley achieves state-of-the-art performance for Foley generation when conditioned on reference audio, while remaining competitive with state-of-the-art video-to-audio methods even without audio conditioning.

This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability is especially crucial in multimedia production, where audio tracks are handled individually for each sound source for precise editing, mixing, and creative control. However, current approaches generate single source-mixed sounds at once, largely because visual features are entangled, and region cues or prompts often fail to specify the source. We propose SelVA, a novel text-conditioned V2A model that treats the text prompt as an explicit selector of target source and modulates video encoder to distinctly extract prompt-relevant video features. The proposed supplementary tokens promote cross-attention by suppressing text-irrelevant activations with efficient parameter tuning, yielding robust semantic and temporal grounding. SelVA further employs a self-augmentation scheme to overcome the lack of mono audio track supervision. We evaluate SelVA on VGG-MONOAUDIO, a curated benchmark of clean single-source videos for such a task. Extensive experiments and ablations consistently verify its effectiveness across audio quality, semantic alignment, and temporal synchronization. Code and demo are available at https://jnwnlee.github.io/selva-demo/.

Automated Audio Captioning (AAC) is the task of generating natural language descriptions given an audio stream. A typical AAC system requires manually curated training data of audio segments and corresponding text caption annotations. The creation of these audio-caption pairs is costly, resulting in general data scarcity for the task. In this work, we address this major limitation and propose an approach to train AAC systems using only text. Our approach leverages the multimodal space of contrastively trained audio-text models, such as CLAP. During training, a decoder generates captions conditioned on the pretrained CLAP text encoder. During inference, the text encoder is replaced with the pretrained CLAP audio encoder. To bridge the modality gap between text and audio embeddings, we propose the use of noise injection or a learnable adapter, during training. We find that the proposed text-only framework performs competitively with state-of-the-art models trained with paired audio, showing that efficient text-to-audio transfer is possible. Finally, we showcase both stylized audio captioning and caption enrichment while training without audio or human-created text captions.

The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Sony AI's publicly released sound effect foundation model, detailing its architecture, training process, and an evaluation against other popular open models. Being optimized for sound effects, we provide (1) a high-quality audio encoder/decoder model and (2) a text-audio alignment model for conditioning, together with (3) text-to-audio and (4) video-to-audio generative models. Distilled text-to-audio and video-to-audio models are also included in the release, allowing for low-resource operation and fast inference. Our evaluation on both public and private data shows competitive or better performance for each module when compared to existing open alternatives like StableAudio-Open and TangoFlux. Inference code and model weights are available at https://github.com/SonyResearch/Woosh. Demo samples can be found at https://sonyresearch.github.io/Woosh/.

Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces noise rather than signal, or on prompt tuning that requires privileged noise annotations unavailable at inference. We address these failures with PRISM (Prototype-Rectified Iterative Self-supervised Manifold Denoising), a training-free, source-free TTA framework grounded in the Affine Noise Hypothesis: severe acoustic noise induces a low-rank affine shift in the multimodal latent space, with more than 90% of distortion energy confined to the leading 60 principal components. PRISM estimates and reverses this distortion from an unlabeled target batch using frozen text prototypes as geometric anchors via three closed-form geometric corrections compiled into a single static projection matrix by Affine Bias Regression. At inference, adaptation reduces to one matrix-vector multiplication in 0.0009 ms, making it substantially faster than gradient-based TTA while requiring no additional training. On UrbanSound8K, PRISM improves over the zero-shot baseline by 12.94 percentage points and surpasses an oracle-assisted TTA baseline by 9.41 percentage points, despite never observing its privileged augmented noise prompts. We further identify the Polyphonic Trap, a principled failure mode of subspace deflation for broadband classes, and resolve it via Confidence-Aware Regression (CAR), recovering up to 8.16 percentage points for the worst-affected class.

We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive generative model that generates audio samples conditioned on text inputs. AudioGen operates on a learnt discrete audio representation. The task of text-to-audio generation poses multiple challenges. Due to the way audio travels through a medium, differentiating ``objects'' can be a difficult task (e.g., separating multiple people simultaneously speaking). This is further complicated by real-world recording conditions (e.g., background noise, reverberation, etc.). Scarce text annotations impose another constraint, limiting the ability to scale models. Finally, modeling high-fidelity audio requires encoding audio at high sampling rate, leading to extremely long sequences. To alleviate the aforementioned challenges we propose an augmentation technique that mixes different audio samples, driving the model to internally learn to separate multiple sources. We curated 10 datasets containing different types of audio and text annotations to handle the scarcity of text-audio data points. For faster inference, we explore the use of multi-stream modeling, allowing the use of shorter sequences while maintaining a similar bitrate and perceptual quality. We apply classifier-free guidance to improve adherence to text. Comparing to the evaluated baselines, AudioGen outperforms over both objective and subjective metrics. Finally, we explore the ability of the proposed method to generate audio continuation conditionally and unconditionally. Samples: https://felixkreuk.github.io/audiogen

Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds aligning with onscreen objects, while V2A cannot generate semantically complete (offscreen sounds missing). In this work, we address the task of holistic audio generation: given a video and a text prompt, we aim to generate both onscreen and offscreen sounds that are temporally synchronized with the video and semantically aligned with text and video. Previous approaches for joint text and video-to-audio generation often suffer from modality bias, favoring one modality over the other. To overcome this limitation, we introduce VinTAGe, a flow-based transformer model that jointly considers text and video to guide audio generation. Our framework comprises two key components: a Visual-Text Encoder and a Joint VT-SiT model. To reduce modality bias and improve generation quality, we employ pretrained uni-modal text-to-audio and video-to-audio generation models for additional guidance. Due to the lack of appropriate benchmarks, we also introduce VinTAGe-Bench, a dataset of 636 video-text-audio pairs containing both onscreen and offscreen sounds. Our comprehensive experiments on VinTAGe-Bench demonstrate that joint text and visual interaction is necessary for holistic audio generation. Furthermore, VinTAGe achieves state-of-the-art results on the VGGSound benchmark. Our source code and pre-trained models will be released. Demo is available at: https://www.youtube.com/watch?v=QmqWhUjPkJI.

Joint audio-video generation aims to synthesize synchronized multisensory content, yet current unified models struggle with fine-grained acoustic control, particularly for identity-preserving speech. Existing approaches either suffer from temporal misalignment due to cascaded generation or lack the capability to perform zero-shot voice cloning within a joint synthesis framework. In this work, we present MM-Sonate, a multimodal flow-matching framework that unifies controllable audio-video joint generation with zero-shot voice cloning capabilities. Unlike prior works that rely on coarse semantic descriptions, MM-Sonate utilizes a unified instruction-phoneme input to enforce strict linguistic and temporal alignment. To enable zero-shot voice cloning, we introduce a timbre injection mechanism that effectively decouples speaker identity from linguistic content. Furthermore, addressing the limitations of standard classifier-free guidance in multimodal settings, we propose a noise-based negative conditioning strategy that utilizes natural noise priors to significantly enhance acoustic fidelity. Empirical evaluations demonstrate that MM-Sonate establishes new state-of-the-art performance in joint generation benchmarks, significantly outperforming baselines in lip synchronization and speech intelligibility, while achieving voice cloning fidelity comparable to specialized Text-to-Speech systems.

Text-guided audio editing aims to modify the language-specified acoustic content while preserving edit-irrelevant source components. Existing training-free methods typically rely on inversion-based editing. While inversion-free editing is appealing as it decreases computational overhead and reconstruction errors, it remains largely unexplored for audio editing. The key challenge is to construct a source-to-target editing path through diffusion denoising dynamics. In this paper, we introduce DirectAudioEdit, the first attempt to develop a training-free and inversion-free method for audio editing. Experiments on music and event-level benchmarks across two backbones show that DirectAudioEdit reduces macro-averaged FAD and KL by 15.9% and 15.8% compared with DDPM inversion, while achieving up to 64.5% editing speedup.

Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in real-world scenarios is often difficult. This data scarcity can degrade model performance under unseen conditions and limit generalization ability. To this end, in this work, we approach this problem from an unsupervised perspective, framing it as a probabilistic inverse problem. Our method requires only diffusion priors trained on individual sources. Separation is then achieved by iteratively guiding an initial state toward the solution through reconstruction guidance. Importantly, we introduce an advanced inverse problem solver specifically designed for separation, which mitigates gradient conflicts caused by interference between the diffusion prior and reconstruction guidance during inverse denoising. This design ensures high-quality and balanced separation performance across individual sources. Additionally, we find that initializing the denoising process with an augmented mixture instead of pure Gaussian noise provides an informative starting point that significantly improves the final performance. To further enhance audio prior modeling, we design a novel time-frequency attention-based network architecture that demonstrates strong audio modeling capability. Collectively, these improvements lead to significant performance gains, as validated across speech-sound event, sound event, and speech separation tasks.

Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance. Specifically, they excel in generating common audio classes while underperforming in the rare ones, thus degrading the overall generation performance. We refer to this problem as long-tailed text-to-audio generation. To address this issue, we propose a simple retrieval-augmented approach for TTA models. Specifically, given an input text prompt, we first leverage a Contrastive Language Audio Pretraining (CLAP) model to retrieve relevant text-audio pairs. The features of the retrieved audio-text data are then used as additional conditions to guide the learning of TTA models. We enhance AudioLDM with our proposed approach and denote the resulting augmented system as Re-AudioLDM. On the AudioCaps dataset, Re-AudioLDM achieves a state-of-the-art Frechet Audio Distance (FAD) of 1.37, outperforming the existing approaches by a large margin. Furthermore, we show that Re-AudioLDM can generate realistic audio for complex scenes, rare audio classes, and even unseen audio types, indicating its potential in TTA tasks.

Despite progress in video-to-audio generation, the field focuses predominantly on mono output, lacking spatial immersion. Existing binaural approaches remain constrained by a two-stage pipeline that first generates mono audio and then performs spatialization, often resulting in error accumulation and spatio-temporal inconsistencies. To address this limitation, we introduce the task of end-to-end binaural spatial audio generation directly from silent video. To support this task, we present the BiAudio dataset, comprising approximately 97K video-binaural audio pairs spanning diverse real-world scenes and camera rotation trajectories, constructed through a semi-automated pipeline. Furthermore, we propose ViSAudio, an end-to-end framework that employs conditional flow matching with a dual-branch audio generation architecture, where two dedicated branches model the audio latent flows. Integrated with a conditional spacetime module, it balances consistency between channels while preserving distinctive spatial characteristics, ensuring precise spatio-temporal alignment between audio and the input video. Comprehensive experiments demonstrate that ViSAudio outperforms existing state-of-the-art methods across both objective metrics and subjective evaluations, generating high-quality binaural audio with spatial immersion that adapts effectively to viewpoint changes, sound-source motion, and diverse acoustic environments. Project website: https://kszpxxzmc.github.io/ViSAudio-project.

Recent advances in video generation have achieved remarkable improvements in visual content fidelity. However, the absence of synchronized audio severely undermines immersive experience and restricts practical applications of these technologies. To address this challenge, several pioneering works have explored diffusion transformer architectures for generating plausible video-synchronized audio, including Kling-foley, HunyuanVideo-foley and Thinksound. Distinct from existing works, we introduce an autoregressive audio generation architecture (DreamFoley) that harnesses the capabilities of large vision-language models (VLMs) to jointly model sequential interactions among video, audio, and text modalities. Our approach features a dual-visual encoder module that effectively captures both audio-aligned and text-aligned visual features. Additionally, we employ a Residual Vector Quantization audio tokenizer with a delay-pattern generation scheme to balance the trade-off between training efficiency and audio quality. Moreover, we introduce the classifier-free guidance strategy into VLMs to bootstrap generated audio quality. Furthermore, we establish an efficient data production pipeline to scale audio-video-text triple collection. Finally, extensive experiments are conducted to validate the effectiveness of our model, achieving promising performance across popular benchmarks. We hope that the findings in this study provide a strong foundation for future video-to-audio generation research. We also release the previously missing audio-visual textual descriptions from the public benchmark, aiming to facilitate subsequent researchers in conducting more convenient and effective evaluations and comparisons.

Large-scale multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio data. In this work, we propose Make-An-Audio with a prompt-enhanced diffusion model that addresses these gaps by 1) introducing pseudo prompt enhancement with a distill-then-reprogram approach, it alleviates data scarcity with orders of magnitude concept compositions by using language-free audios; 2) leveraging spectrogram autoencoder to predict the self-supervised audio representation instead of waveforms. Together with robust contrastive language-audio pretraining (CLAP) representations, Make-An-Audio achieves state-of-the-art results in both objective and subjective benchmark evaluation. Moreover, we present its controllability and generalization for X-to-Audio with "No Modality Left Behind", for the first time unlocking the ability to generate high-definition, high-fidelity audios given a user-defined modality input. Audio samples are available at https://Text-to-Audio.github.io

Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g. generating text not grounded in the audio input. We analyze these grounding failures and identify a distinct taxonomy: Event Omission, False Event Identity, Temporal Relation Error, and Quantitative Temporal Error. To address this, we introduce the AHA (Audio Hallucination Alignment) framework. By leveraging counterfactual hard negative mining, our pipeline constructs a high-quality preference dataset that forces models to distinguish strict acoustic evidence from linguistically plausible fabrications. Additionally, we establish AHA-Eval, a diagnostic benchmark designed to rigorously test these fine-grained temporal reasoning capabilities. We apply this data to align Qwen2.5-Omni. The resulting model, Qwen-Audio-AHA, achieves a 13.7% improvement on AHA-Eval. Crucially, this benefit generalizes beyond our diagnostic set. Our model shows substantial gains on public benchmarks, including 1.3% on MMAU-Test and 1.6% on MMAR, outperforming latest SOTA methods.

Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a single model to target multiple sources, they have difficulty generalizing to unseen sources. In this paper, we propose a three-component pipeline to train a universal audio source separator from a large, but weakly-labeled dataset: AudioSet. First, we propose a transformer-based sound event detection system for processing weakly-labeled training data. Second, we devise a query-based audio separation model that leverages this data for model training. Third, we design a latent embedding processor to encode queries that specify audio targets for separation, allowing for zero-shot generalization. Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training. In addition, the proposed audio separator can be used in a zero-shot setting, learning to separate types of audio sources that were never seen in training. To evaluate the separation performance, we test our model on MUSDB18, while training on the disjoint AudioSet. We further verify the zero-shot performance by conducting another experiment on audio source types that are held-out from training. The model achieves comparable Source-to-Distortion Ratio (SDR) performance to current supervised models in both cases.

In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer that operates on latent features. SoloAudio supports both audio-oriented and language-oriented TSE by utilizing a CLAP model as the feature extractor for target sounds. Furthermore, SoloAudio leverages synthetic audio generated by state-of-the-art text-to-audio models for training, demonstrating strong generalization to out-of-domain data and unseen sound events. We evaluate this approach on the FSD Kaggle 2018 mixture dataset and real data from AudioSet, where SoloAudio achieves the state-of-the-art results on both in-domain and out-of-domain data, and exhibits impressive zero-shot and few-shot capabilities. Source code and demos are released.

Current video-to-audio (V2A) methods struggle in complex multi-event scenarios (video scenarios involving multiple sound sources, sound events, or transitions) due to two critical limitations. First, existing methods face challenges in precisely aligning intricate semantic information together with rapid dynamic features. Second, foundational training lacks quantitative preference optimization for semantic-temporal alignment and audio quality. As a result, it fails to enhance integrated generation quality in cluttered multi-event scenes. To address these core limitations, this study proposes a novel V2A framework: MultiSoundGen. It introduces direct preference optimization (DPO) into the V2A domain, leveraging audio-visual pretraining (AVP) to enhance performance in complex multi-event scenarios. Our contributions include two key innovations: the first is SlowFast Contrastive AVP (SF-CAVP), a pioneering AVP model with a unified dual-stream architecture. SF-CAVP explicitly aligns core semantic representations and rapid dynamic features of audio-visual data to handle multi-event complexity; second, we integrate the DPO method into V2A task and propose AVP-Ranked Preference Optimization (AVP-RPO). It uses SF-CAVP as a reward model to quantify and prioritize critical semantic-temporal matches while enhancing audio quality. Experiments demonstrate that MultiSoundGen achieves state-of-the-art (SOTA) performance in multi-event scenarios, delivering comprehensive gains across distribution matching, audio quality, semantic alignment, and temporal synchronization. Demos are available at https://v2aresearch.github.io/MultiSoundGen/.

The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semantically aligned features, then train an LDM with CAVP-aligned visual features on spectrogram latent space. The CAVP-aligned features enable LDM to capture the subtler audio-visual correlation via a cross-attention module. We further significantly improve sample quality with `double guidance'. Diff-Foley achieves state-of-the-art V2A performance on current large scale V2A dataset. Furthermore, we demonstrate Diff-Foley practical applicability and generalization capabilities via downstream finetuning. Project Page: see https://diff-foley.github.io/

This paper presents VoiceLDM, a model designed to produce audio that accurately follows two distinct natural language text prompts: the description prompt and the content prompt. The former provides information about the overall environmental context of the audio, while the latter conveys the linguistic content. To achieve this, we adopt a text-to-audio (TTA) model based on latent diffusion models and extend its functionality to incorporate an additional content prompt as a conditional input. By utilizing pretrained contrastive language-audio pretraining (CLAP) and Whisper, VoiceLDM is trained on large amounts of real-world audio without manual annotations or transcriptions. Additionally, we employ dual classifier-free guidance to further enhance the controllability of VoiceLDM. Experimental results demonstrate that VoiceLDM is capable of generating plausible audio that aligns well with both input conditions, even surpassing the speech intelligibility of the ground truth audio on the AudioCaps test set. Furthermore, we explore the text-to-speech (TTS) and zero-shot text-to-audio capabilities of VoiceLDM and show that it achieves competitive results. Demos and code are available at https://voiceldm.github.io.

Speech Language Models (SLMs) are increasingly deployed in multi-speaker environments, yet their ability to attribute speech to the correct speaker and reason over speaker identities remains unclear. Hence, we introduce HEAR, a conceptually hierarchical benchmark diagnosing the foundational capabilities of speaker-attributed reasoning, comprising 2.4K human-verified samples from 887 diverse multi-party audio clips. Evaluating 20 leading SLMs on HEAR reveals they struggle with these foundational tasks, often relying on semantic priors rather than actual vocal cues. To address this, we present A2R, a 30B model optimized on Counterfactual Audio with Speaker-level Hard negatives (CASH), a dataset designed to guide the model to prioritize acoustic vocal cues over linguistic signals. A2R achieves strong performance on HEAR and exhibits zero-shot generalization to diverse multi-speaker downstream tasks, demonstrating that learned speaker attribution unlocks the model's latent capacity for speaker-aware reasoning. All resources are available at https://attributetoreason.github.io/AttributeToReason/

In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to ignore all interfering speech and noise, but the target speaker. A naive approach is to require a clean speech example to enroll the target speaker. This is however not well aligned with the hearable application domain since obtaining a clean example is challenging in real world scenarios, creating a unique user interface problem. We present the first enrollment interface where the wearer looks at the target speaker for a few seconds to capture a single, short, highly noisy, binaural example of the target speaker. This noisy example is used for enrollment and subsequent speech extraction in the presence of interfering speakers and noise. Our system achieves a signal quality improvement of 7.01 dB using less than 5 seconds of noisy enrollment audio and can process 8 ms of audio chunks in 6.24 ms on an embedded CPU. Our user studies demonstrate generalization to real-world static and mobile speakers in previously unseen indoor and outdoor multipath environments. Finally, our enrollment interface for noisy examples does not cause performance degradation compared to clean examples, while being convenient and user-friendly. Taking a step back, this paper takes an important step towards enhancing the human auditory perception with artificial intelligence. We provide code and data at: https://github.com/vb000/LookOnceToHear.

Recent advancements in latent diffusion models (LDMs) have markedly enhanced text-to-audio generation, yet their iterative sampling processes impose substantial computational demands, limiting practical deployment. While recent methods utilizing consistency-based distillation aim to achieve few-step or single-step inference, their one-step performance is constrained by curved trajectories, preventing them from surpassing traditional diffusion models. In this work, we introduce FlashAudio with rectified flows to learn straight flow for fast simulation. To alleviate the inefficient timesteps allocation and suboptimal distribution of noise, FlashAudio optimizes the time distribution of rectified flow with Bifocal Samplers and proposes immiscible flow to minimize the total distance of data-noise pairs in a batch vias assignment. Furthermore, to address the amplified accumulation error caused by the classifier-free guidance (CFG), we propose Anchored Optimization, which refines the guidance scale by anchoring it to a reference trajectory. Experimental results on text-to-audio generation demonstrate that FlashAudio's one-step generation performance surpasses the diffusion-based models with hundreds of sampling steps on audio quality and enables a sampling speed of 400x faster than real-time on a single NVIDIA 4090Ti GPU.

Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by distilling a one-step consistency model from a multi-step diffusion-based teacher model. However, distilled consistency models are inherently biased towards the sampling trajectory of the teacher model, making them less robust to noise and prone to inheriting inaccuracies from the teacher model. To address this limitation, we propose ROSE-CD: Robust One-step Speech Enhancement via Consistency Distillation, a novel approach for distilling a one-step consistency model. Specifically, we introduce a randomized learning trajectory to improve the model's robustness to noise. Furthermore, we jointly optimize the one-step model with two time-domain auxiliary losses, enabling it to recover from teacher-induced errors and surpass the teacher model in overall performance. This is the first pure one-step consistency distillation model for diffusion-based speech enhancement, achieving 54 times faster inference speed and superior performance compared to its 30-step teacher model. Experiments on the VoiceBank-DEMAND dataset demonstrate that the proposed model achieves state-of-the-art performance in terms of speech quality. Moreover, its generalization ability is validated on both an out-of-domain dataset and real-world noisy recordings.

Sound content is an indispensable element for multimedia works such as video games, music, and films. Recent high-quality diffusion-based sound generation models can serve as valuable tools for the creators. However, despite producing high-quality sounds, these models often suffer from slow inference speeds. This drawback burdens creators, who typically refine their sounds through trial and error to align them with their artistic intentions. To address this issue, we introduce Sound Consistency Trajectory Models (SoundCTM). Our model enables flexible transitioning between high-quality 1-step sound generation and superior sound quality through multi-step generation. This allows creators to initially control sounds with 1-step samples before refining them through multi-step generation. While CTM fundamentally achieves flexible 1-step and multi-step generation, its impressive performance heavily depends on an additional pretrained feature extractor and an adversarial loss, which are expensive to train and not always available in other domains. Thus, we reframe CTM's training framework and introduce a novel feature distance by utilizing the teacher's network for a distillation loss. Additionally, while distilling classifier-free guided trajectories, we train conditional and unconditional student models simultaneously and interpolate between these models during inference. We also propose training-free controllable frameworks for SoundCTM, leveraging its flexible sampling capability. SoundCTM achieves both promising 1-step and multi-step real-time sound generation without using any extra off-the-shelf networks. Furthermore, we demonstrate SoundCTM's capability of controllable sound generation in a training-free manner.

Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references are available. While recent controllable TTS methods attempt to address this issue, they typically rely on absolute style targets and discrete textual prompts, and therefore do not support continuous and reference-relative style control. We propose ReStyle-TTS, a framework that enables continuous and reference-relative style control in zero-shot TTS. Our key insight is that effective style control requires first reducing the model's implicit dependence on reference style before introducing explicit control mechanisms. To this end, we introduce Decoupled Classifier-Free Guidance (DCFG), which independently controls text and reference guidance, reducing reliance on reference style while preserving text fidelity. On top of this, we apply style-specific LoRAs together with Orthogonal LoRA Fusion to enable continuous and disentangled multi-attribute control, and introduce a Timbre Consistency Optimization module to mitigate timbre drift caused by weakened reference guidance. Experiments show that ReStyle-TTS enables user-friendly, continuous, and relative control over pitch, energy, and multiple emotions while maintaining intelligibility and speaker timbre, and performs robustly in challenging mismatched reference-target style scenarios.

Existing single-domain and multi-task audio systems remain limited in directly organizing heterogeneous audio components, ambience, and multiple roles into long-form temporal scenes. We present Qwen-Audio-3.0-Gen-Preview, a unified non-autoregressive framework that uses a Diffusion Transformer (DiT) and a shared variational autoencoder (VAE) to generate the complete mixed waveform. Prompt enhancement converts free-form requests into structured temporal records that are rendered as textual conditions, while a two-stage data curriculum and semantic conditional views train the proposed model to use these conditions across standalone and mixed-scene audio. A shared continuous VAE compresses 48kHz stereo waveforms into 25Hz latent sequences and incorporates semantic supervision, providing one representation for heterogeneous audio. On the public reference-conditioned benchmark, speaker similarity is the proposed model's clearest strength across all three subsets. Across the multi-speaker and rich-timeline benchmarks, its clearest comparative strengths are cross-turn consistency in both languages and temporal localization, respectively. On AudioCaps, its advantages are concentrated in evaluations using large audio-language models and AudioBox. These results demonstrate the potential of unified generation for temporally structured audio without task-specific branches.

Large Audio Language Models (LALMs) represent an important frontier in multimodal AI, addressing diverse audio tasks. Recently, post-training of LALMs has received increasing attention due to significant performance improvements over foundation models. While single-stage post-training such as reinforcement learning (RL) has demonstrated promising results, multi-stage approaches such as supervised fine-tuning (SFT) followed by RL remain suboptimal. The allocation of data across multiple training stages to maximize LALM capabilities has not been fully explored, and large-scale, high-quality datasets for such research are also lacking. To address these problems, we firstly present AudioMCQ, a comprehensive audio multiple-choice question dataset comprising 571k samples with two kinds of chain-of-thought annotations. Secondly, we investigate the prevalent zero audio-contribution phenomenon in LALMs, where models derive correct answers solely from textual information without processing audio content. We propose Audio-Contribution Filtering to partition data into weak and strong audio-contribution subsets. Based on these insights, we develop two effective post-training paradigms: Weak-to-Strong (SFT on weak audio-contribution data followed by RL on strong audio-contribution data) and Mixed-to-Strong (SFT on mixed audio-contribution data followed by RL on strong audio-contribution data). We achieve first place in the DCASE 2025 Audio-Question-Answering challenge by using AudioMCQ. Additionally, leveraging our dataset with different training strategies, we achieve 78.2\% on MMAU-test-mini, 75.6\% on MMAU, 67.1\% on MMAR, and 70.7\% on MMSU, establishing new state-of-the-art performance across these benchmarks.

With the growing use of voice-activated systems and speech recognition technologies, the danger of backdoor attacks on audio data has grown significantly. This research looks at a specific type of attack, known as a Stochastic investment-based backdoor attack (MarketBack), in which adversaries strategically manipulate the stylistic properties of audio to fool speech recognition systems. The security and integrity of machine learning models are seriously threatened by backdoor attacks, in order to maintain the reliability of audio applications and systems, the identification of such attacks becomes crucial in the context of audio data. Experimental results demonstrated that MarketBack is feasible to achieve an average attack success rate close to 100% in seven victim models when poisoning less than 1% of the training data.

Audio Language Models (ALMs) have recently shown strong capabilities in unified reasoning over speech, sound, and natural language; yet they inherit behavioral issues observed in Large Language Models, including sycophancy--the tendency to agree with user assertions even when they contradict objective evidence. While sycophancy has been extensively studied in text and vision-language models, its manifestation in audio-conditioned reasoning remains largely unexplored, despite the need for ALMs to rely on auditory cues such as acoustic events, speaker characteristics, and speech rate. To address this gap, we introduce SYAUDIO, the first benchmark dedicated to evaluating sycophancy in ALMs, consisting of 4,319 audio questions spanning Audio Perception, Audio Reasoning, Audio Math, and Audio Ethics. Built upon established audio benchmarks and augmented with TTS-generated arithmetic and moral reasoning tasks, SYAUDIO enables systematic evaluation across multiple domains and sycophancy types with carefully verified data quality. Furthermore, we analyze audio-specific sycophancy under realistic conditions involving noise and rate, and demonstrate that supervised fine-tuning with chain-of-thought data is an effective mitigation strategy for reducing sycophantic behavior in ALMs.

Generating lifelike conversational avatars requires modeling not just isolated speakers, but the dynamic, reciprocal interaction of speaking and listening. However, modeling the listener is exceptionally challenging: direct audio-driven training fails, producing stiff, static listening motions. This failure stems from a fundamental imbalance: the speaker's motion is strongly driven by speech audio, while the listener's motion primarily follows an internal motion prior and is only loosely guided by external speech. This challenge has led most methods to focus on speak-only generation. The only prior attempt at joint generation relies on extra speaker's motion to produce the listener. This design is not end-to-end, thereby hindering the real-time applicability. To address this limitation, we present UniLS, the first end-to-end framework for generating unified speak-listen expressions, driven by only dual-track audio. Our method introduces a novel two-stage training paradigm. Stage 1 first learns the internal motion prior by training an audio-free autoregressive generator, capturing the spontaneous dynamics of natural facial motion. Stage 2 then introduces the dual-track audio, fine-tuning the generator to modulate the learned motion prior based on external speech cues. Extensive evaluations show UniLS achieves state-of-the-art speaking accuracy. More importantly, it delivers up to 44.1\% improvement in listening metrics, generating significantly more diverse and natural listening expressions. This effectively mitigates the stiffness problem and provides a practical, high-fidelity audio-driven solution for interactive digital humans.

Recent advancements in audio-aware large language models (ALLMs) enable them to process and understand audio inputs. However, these models often hallucinate non-existent sound events, reducing their reliability in real-world applications. To address this, we propose LISTEN (Learning to Identify Sounds Through Extended Negative Samples), a contrastive-like training method that enhances ALLMs' ability to distinguish between present and absent sounds using synthesized data from the backbone LLM. Unlike prior approaches, our method requires no modification to LLM parameters and efficiently integrates audio representations via a lightweight adapter. Experiments show that LISTEN effectively mitigates hallucinations while maintaining impressive performance on existing audio question and reasoning benchmarks. At the same time, it is more efficient in both data and computation.

Large audio-language models (LALMs) unify speech and text processing, but their robustness in noisy real-world settings remains underexplored. We investigate how irrelevant audio, such as silence, synthetic noise, and environmental sounds, affects text reasoning tasks where audio is unnecessary. Across three text-based benchmarks, we find that even non-informative audio reduces accuracy and increases prediction volatility; the severity of interference scales with longer durations, higher amplitudes, and elevated decoding temperatures. Silence, often assumed neutral, destabilizes outputs as strongly as synthetic noise. While larger models show greater resilience, vulnerabilities persist across all evaluated systems. We further test mitigation strategies and find that prompting shows limited effectiveness, whereas self-consistency improves stability at the cost of increased computation. Our results reveal cross-modal interference as a key robustness challenge and highlight the need for efficient fusion strategies that preserve reasoning performance in the presence of irrelevant inputs.

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop with multi-source training mixtures due to the lack of supervision signal for single source separation cases during training. However, in the case of language-conditional audio separation, we do have access to corresponding text descriptions for each audio mixture in our training data, which can be seen as (rough) representations of the audio samples in the language modality. To this end, in this paper, we propose a generic bi-modal separation framework which can enhance the existing unsupervised frameworks to separate single-source signals in a target modality (i.e., audio) using the easily separable corresponding signals in the conditioning modality (i.e., language), without having access to single-source samples in the target modality during training. We empirically show that this is well within reach if we have access to a pretrained joint embedding model between the two modalities (i.e., CLAP). Furthermore, we propose to incorporate our framework into two fundamental scenarios to enhance separation performance. First, we show that our proposed methodology significantly improves the performance of purely unsupervised baselines by reducing the distribution shift between training and test samples. In particular, we show that our framework can achieve 71% boost in terms of Signal-to-Distortion Ratio (SDR) over the baseline, reaching 97.5% of the supervised learning performance. Second, we show that we can further improve the performance of the supervised learning itself by 17% if we augment it by our proposed weakly-supervised framework, that enables a powerful semi-supervised framework for audio separation.

Query-based universal sound separation is fundamental to intelligent auditory systems, aiming to isolate specific sources from mixtures. Despite recent advances, existing methods continue to suffer from residual interference in complex acoustic scenes. This performance limitation stems largely from a data bottleneck: in-the-wild datasets contain weak labels and severe co-occurrence of events. These flaws induce models to learn spurious correlations between background noise and target categories instead of robust acoustic features. To address this, we propose an automated pipeline that eliminates co-occurrence of events by mining high-purity single-event segments from in-the-wild datasets via a semantically consistent synthesis protocol. Utilizing this pipeline, we constructed Hive, a high-quality synthetic dataset comprising 2.4k hours of raw audio. Experimental results demonstrate that, compared with the state-of-the-art model SAM-Audio which was trained on a huge dataset sim500 times larger than Hive, certain open-source models trained on Hive achieve competitive separation accuracy and perceptual quality. Moreover, these models exhibited remarkable zero-shot generalization on out-of-distribution evaluation benchmarks. These findings highlight that prioritizing purity of supervised signals enables significant data efficiency, offering a new paradigm for training robust auditory foundation models with reduced computational costs. Code and dataset are available at https://shandaai.github.io/Hive.

Long-form and real-time talking-head generation remains challenging due to a latency-quality trade-off: inefficient multi-step diffusion prohibits streaming generation, whereas real-time autoregressive approaches suffer from error accumulation and identity drift. To address this drawback, we propose LeapTalk, a novel framework that achieves stable and real-time talking-head generation with a single forward step, scaling to arbitrarily long videos. At the heart of our approach lies a single-step bridge distillation scheme. On the one hand, departing from the conventional noise-to-data paradigm, we introduce a data-to-data transport formulation based on a Brownian bridge. Anchored by a persistent reference, this strategy effectively mitigates identity drift and enhances long-term temporal stability. On the other hand, to enable smooth knowledge transfer from a pre-trained diffusion teacher to the student bridge model, we explore a heterogeneous distillation framework with an SNR-aligned time transformation Φ(τ), which bridges the functional discrepancy between the two models. Moreover, we propose an audio-driven classifier-free guidance mechanism to maintain fine-grained lip synchronization under extreme step reduction. Extensive experiments demonstrate that our method achieves high-fidelity and temporally consistent video generation with only 1 step at up to 200 FPS, significantly outperforming existing approaches in both efficiency and stability. Project Page: https://zhangrongxiang.github.io/leaptalk-page/

Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data and struggle to generalize to the immense variability and open-set nature of real-world acoustic scenes. Inspired by the success of generative foundation models, we investigate whether pre-trained text-guided audio diffusion models can overcome these limitations. We make a surprising discovery: zero-shot source separation can be achieved purely through a pre-trained text-guided audio diffusion model under the right configuration. Our method, named ZeroSep, works by inverting the mixed audio into the diffusion model's latent space and then using text conditioning to guide the denoising process to recover individual sources. Without any task-specific training or fine-tuning, ZeroSep repurposes the generative diffusion model for a discriminative separation task and inherently supports open-set scenarios through its rich textual priors. ZeroSep is compatible with a variety of pre-trained text-guided audio diffusion backbones and delivers strong separation performance on multiple separation benchmarks, surpassing even supervised methods.

Prevailing Video-to-Audio (V2A) generation models operate offline, assuming an entire video sequence or chunks of frames are available beforehand. This critically limits their use in interactive applications such as live content creation and emerging generative world models. To address this gap, we introduce the novel task of frame-level online V2A generation, where a model autoregressively generates audio from video without access to future video frames. Furthermore, we propose SoundReactor, which, to the best of our knowledge, is the first simple yet effective framework explicitly tailored for this task. Our design enforces end-to-end causality and targets low per-frame latency with audio-visual synchronization. Our model's backbone is a decoder-only causal transformer over continuous audio latents. For vision conditioning, it leverages grid (patch) features extracted from the smallest variant of the DINOv2 vision encoder, which are aggregated into a single token per frame to maintain end-to-end causality and efficiency. The model is trained through a diffusion pre-training followed by consistency fine-tuning to accelerate the diffusion head decoding. On a benchmark of diverse gameplay videos from AAA titles, our model successfully generates semantically and temporally aligned, high-quality full-band stereo audio, validated by both objective and human evaluations. Furthermore, our model achieves low per-frame waveform-level latency (26.3ms with the head NFE=1, 31.5ms with NFE=4) on 30FPS, 480p videos using a single H100. Demo samples are available at https://koichi-saito-sony.github.io/soundreactor/.

DCASE~2026 Task~5 introduces Audio-Dependent Question Answering (ADQA), which tests whether large audio-language models answer from the audio rather than from textual priors. An Audio-Dependency Filtering (ADF) pipeline combines silent-audio probing, per-option perplexity, a large language model (LLM) commonsense check, and human review to remove items solvable from text alone. The 3000 items that pass form the ADQA-Bench evaluation set, spanning music, speech, and environmental audio. The inaugural edition draws 14 teams and 36 submissions across two tracks defined by total parameter count (up to 100B and under 10B). A Chung-Ang University ensemble of MOSS-Audio-8B-Thinking and Qwen3-Omni-30B reaches the top overall accuracy at 58.33, and a MOSS-only configuration from the same team leads the sub-10B track at 57.30. Across the 30 submissions with a comparable development score, evaluation accuracy falls by 11.91 percentage points (pp) on average (median 10.91\,pp) on the hidden evaluation split, which is designed to be harder than the development split. The most common building blocks are: the MOSS-Audio-8B-Thinking backbone (13 of 36 submissions), Low-Rank Adaptation (LoRA) fine-tuning on AudioMCQ-StrongAC, and preference or reinforcement-learning objectives -- Group Relative Policy Optimization (GRPO) in five teams, Group reward-Decoupled Normalization Policy Optimization (GDPO) in two. At test time, prompt engineering is near-universal, and majority or choice-permutation voting is common. Every system misses the same set of 233 evaluation items.

Recent advancements in large audio-language models (LALMs) have enabled speech-based user interactions, significantly enhancing user experience and accelerating the deployment of LALMs in real-world applications. However, ensuring the safety of LALMs is crucial to prevent risky outputs that may raise societal concerns or violate AI regulations. Despite the importance of this issue, research on jailbreaking LALMs remains limited due to their recent emergence and the additional technical challenges they present compared to attacks on DNN-based audio models. Specifically, the audio encoders in LALMs, which involve discretization operations, often lead to gradient shattering, hindering the effectiveness of attacks relying on gradient-based optimizations. The behavioral variability of LALMs further complicates the identification of effective (adversarial) optimization targets. Moreover, enforcing stealthiness constraints on adversarial audio waveforms introduces a reduced, non-convex feasible solution space, further intensifying the challenges of the optimization process. To overcome these challenges, we develop AdvWave, the first jailbreak framework against LALMs. We propose a dual-phase optimization method that addresses gradient shattering, enabling effective end-to-end gradient-based optimization. Additionally, we develop an adaptive adversarial target search algorithm that dynamically adjusts the adversarial optimization target based on the response patterns of LALMs for specific queries. To ensure that adversarial audio remains perceptually natural to human listeners, we design a classifier-guided optimization approach that generates adversarial noise resembling common urban sounds. Extensive evaluations on multiple advanced LALMs demonstrate that AdvWave outperforms baseline methods, achieving a 40% higher average jailbreak attack success rate.

Text-guided audio editing aims to modify specific acoustic events while strictly preserving non-target content. Despite recent progress, existing approaches remain fundamentally limited. Training-free methods often suffer from signal degradation caused by diffusion inversion, while training-based methods, although achieving higher generation quality, are severely constrained by the scarcity of high-quality paired data and task formulations that cover only a narrow subset of editing operations. In addition, standard architectures typically decouple text and audio processing, limiting the ability to align instructions with specific acoustic contexts. To address these challenges, we propose MMEdit, an audio-language-model-driven framework for unified audio editing. We systematically extend task definitions to cover a comprehensive range of editing operations, including addition, replacement, removal, reordering, and attribute modification. Furthermore, we design a scalable data synthesis pipeline to construct large-scale paired datasets with fine-grained event-level annotations. To capture complex editing semantics, we integrate a Qwen2-Audio encoder with an MMDiT-based generator, enabling precise cross-modal alignment and localized editing. Experimental results demonstrate that our method achieves superior editing localization accuracy, robust instruction following, and high fidelity in non-edited regions.

The sound effects that designers add to videos are designed to convey a particular artistic effect and, thus, may be quite different from a scene's true sound. Inspired by the challenges of creating a soundtrack for a video that differs from its true sound, but that nonetheless matches the actions occurring on screen, we propose the problem of conditional Foley. We present the following contributions to address this problem. First, we propose a pretext task for training our model to predict sound for an input video clip using a conditional audio-visual clip sampled from another time within the same source video. Second, we propose a model for generating a soundtrack for a silent input video, given a user-supplied example that specifies what the video should "sound like". We show through human studies and automated evaluation metrics that our model successfully generates sound from video, while varying its output according to the content of a supplied example. Project site: https://xypb.github.io/CondFoleyGen/

Voice agents must call tools and hold multi-turn dialogue entirely through speech, yet the dominant paradigm trains them in text. Existing frameworks either cascade TTS and ASR around a proprietary voice API, where gradients cannot flow and per-call cost makes on-policy reinforcement learning prohibitive, or stay in text: they measure voice agents but cannot improve them. We present SpeechGym, an audio-native agentic environment in which two omni-modal models converse in native audio, with no external ASR or TTS and no API boundary, over the unmodified tasks, tools and success check of an established text agentic benchmark, so that the interaction modality is the only variable and the loop stays local and trainable end to end. Audio agentic capability does not follow from audio understanding. The failures speech introduces are perceptual rather than reasoning deficits: the agent picks the right tool and the right argument slot but fills it with a value misheard from the waveform, and that single error cascades into a failed call, a retry of the same call, and a wasted step budget. A second failure is behavioural: under an insistent caller the agent performs an unauthorised write and ends the episode believing it helped. Both are trainable, because the environment labels them for free: a call with a misheard argument fails against the database while a correct one succeeds. The obstacle is sparsity, not signal. Outcome-only GRPO is gradient-starved here, since almost every rollout group fails identically, while a per-turn process reward crediting each successful tool call restores variance to nearly every group. Trained this way, the agent transfers with no further tuning to an independently implemented voice benchmark, more than doubling task success and carrying an open-weights model from last place to second on that leaderboard, while using fewer turns and tokens than before training.

Large audio-language models (LALMs) have demonstrated strong capabilities in understanding diverse audio inputs. This diversity includes low-frequency signals that are inaudible to humans but can still enter the model and influence its generation. However, the practical impact of such low-frequency inputs on LALMs remains largely unexplored. In this paper, we propose Intermittent Low-Frequency Lockout (ILL), an inaudible red teaming method that evaluates this risk using a universal waveform template in a black box setting. ILL uses Sentence Attention Scale Estimation to determine active intervals and Frequency Confusion Transfer to construct a low-frequency waveform with continuous phase from corpus spectral variation. To mitigate this risk, we propose Distributional Requery Guard (DRG) to detect low-frequency distribution shifts and conditionally request a second recording for semantic recovery. Across six LALMs and multiple audio understanding tasks, ILL reduces accuracy by up to 67 percentage points while receiving a mean human audibility rating of 1.33, close to 1.17 for clean audio; DRG raises mean attacked accuracy from 28.5\% to 46.1\% after clean reacquisition. These findings identify a previously overlooked safety risk for LALMs and provide a foundation for future research on robust audio understanding.

The rapid advancement of generative audio models has outpaced the development of robust evaluation methodologies. Existing objective metrics and general multimodal large language models (MLLMs) often struggle with domain generalization, zero-shot capabilities, and instructional flexibility. To address these bottlenecks, we propose JASTIN, a generalizable, instruction-driven audio evaluation framework that formulates audio assessment as a self-instructed reasoning task. JASTIN bridges a frozen high-performance audio encoder with a fine-tuned LLM backbone via a trainable audio adapter. To ensure robust zero-shot generalization, we introduce a comprehensive instruction following data preparation pipeline, incorporating Multi-Source, Multi-Task, Multi-Calibration, and Multi-Description data. Experimental results demonstrate that JASTIN achieves state-of-the-art Pearson and Spearman correlations with human subjective ratings. It consistently outperforms general MLLMs across speech, sound, music, and out-of-domain evaluation tasks without the need for task-specific retraining.

The Text to Audible-Video Generation (TAVG) task involves generating videos with accompanying audio based on text descriptions. Achieving this requires skillful alignment of both audio and video elements. To support research in this field, we have developed a comprehensive Text to Audible-Video Generation Benchmark (TAVGBench), which contains over 1.7 million clips with a total duration of 11.8 thousand hours. We propose an automatic annotation pipeline to ensure each audible video has detailed descriptions for both its audio and video contents. We also introduce the Audio-Visual Harmoni score (AVHScore) to provide a quantitative measure of the alignment between the generated audio and video modalities. Additionally, we present a baseline model for TAVG called TAVDiffusion, which uses a two-stream latent diffusion model to provide a fundamental starting point for further research in this area. We achieve the alignment of audio and video by employing cross-attention and contrastive learning. Through extensive experiments and evaluations on TAVGBench, we demonstrate the effectiveness of our proposed model under both conventional metrics and our proposed metrics.

Current leading Text-To-Audio (TTA) generation models suffer from degraded performance on zero-shot and few-shot settings. It is often challenging to generate high-quality audio for audio events that are unseen or uncommon in the training set. Inspired by the success of Retrieval-Augmented Generation (RAG) in Large Language Model (LLM)-based knowledge-intensive tasks, we extend the TTA process with additional conditioning contexts. We propose Audiobox TTA-RAG, a novel retrieval-augmented TTA approach based on Audiobox, a conditional flow-matching audio generation model. Unlike the vanilla Audiobox TTA solution which generates audio conditioned on text, we augmented the conditioning input with retrieved audio samples that provide additional acoustic information to generate the target audio. Our retrieval method does not require the external database to have labeled audio, offering more practical use cases. To evaluate our proposed method, we curated test sets in zero-shot and few-shot settings. Our empirical results show that the proposed model can effectively leverage the retrieved audio samples and significantly improve zero-shot and few-shot TTA performance, with large margins on multiple evaluation metrics, while maintaining the ability to generate semantically aligned audio for the in-domain setting. In addition, we investigate the effect of different retrieval methods and data sources.

Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems typically rely on fixed-frame-rate acoustic tokenization, resulting in speech sequences that are significantly longer than, and asynchronous with their corresponding text. Beyond computational inefficiency, this sequence length disparity often triggers hallucinations in TTS and amplifies the modality gap in spoken language modeling (SLM). In this paper, we propose a novel tokenization scheme that establishes one-to-one synchronization between continuous acoustic features and text tokens, enabling unified, single-stream modeling within an LLM. We demonstrate that these synchronous tokens maintain high-fidelity audio reconstruction and can be effectively modeled in a latent space by a large language model with a flow matching head. Moreover, the ability to seamlessly toggle speech modality within the context enables text-only guidance--a technique that blends logits from text-only and text-speech modes to flexibly bridge the gap toward text-only LLM intelligence. Experimental results indicate that our approach achieves performance competitive with state-of-the-art TTS and SLM systems while virtually eliminating content hallucinations and preserving linguistic integrity, all at a significantly reduced inference cost.

Audio editing is applicable for various purposes, such as adding background sound effects, replacing a musical instrument, and repairing damaged audio. Recently, some diffusion-based methods achieved zero-shot audio editing by using a diffusion and denoising process conditioned on the text description of the output audio. However, these methods still have some problems: 1) they have not been trained on editing tasks and cannot ensure good editing effects; 2) they can erroneously modify audio segments that do not require editing; 3) they need a complete description of the output audio, which is not always available or necessary in practical scenarios. In this work, we propose AUDIT, an instruction-guided audio editing model based on latent diffusion models. Specifically, AUDIT has three main design features: 1) we construct triplet training data (instruction, input audio, output audio) for different audio editing tasks and train a diffusion model using instruction and input (to be edited) audio as conditions and generating output (edited) audio; 2) it can automatically learn to only modify segments that need to be edited by comparing the difference between the input and output audio; 3) it only needs edit instructions instead of full target audio descriptions as text input. AUDIT achieves state-of-the-art results in both objective and subjective metrics for several audio editing tasks (e.g., adding, dropping, replacement, inpainting, super-resolution). Demo samples are available at https://audit-demo.github.io/.

Audio has rapidly become a primary interface for foundation models, powering real-time voice assistants. Ensuring safety in audio systems is inherently more complex than just "unsafe text spoken aloud": real-world risks can hinge on audio-native harmful sound events, speaker attributes (e.g., child voice), impersonation/voice-cloning misuse, and voice-content compositional harms, such as child voice plus sexual content. The nature of audio makes it challenging to develop comprehensive benchmarks or guardrails against this unique risk landscape. To close this gap, we conduct large-scale red teaming on audio systems, systematically uncover vulnerabilities in audio, and develop a comprehensive, policy-grounded audio risk taxonomy and AudioSafetyBench, the first policy-based audio safety benchmark across diverse threat models. AudioSafetyBench supports diverse languages, suspicious voices (e.g., celebrity/impersonation and child voice), risky voice-content combinations, and non-speech sound events. To defend against these threats, we propose AudioGuard, a unified guardrail consisting of 1) SoundGuard for waveform-level audio-native detection and 2) ContentGuard for policy-grounded semantic protection. Extensive experiments on AudioSafetyBench and four complementary benchmarks show that AudioGuard consistently improves guardrail accuracy over strong audio-LLM-based baselines with substantially lower latency.

Visual sound source localization is a fundamental perception task that aims to detect the location of sounding sources in a video given its audio. Despite recent progress, we identify two shortcomings in current methods: 1) most approaches perform poorly in cases with low audio-visual semantic correspondence such as silence, noise, and offscreen sounds, i.e. in the presence of negative audio; and 2) most prior evaluations are limited to positive cases, where both datasets and metrics convey scenarios with a single visible sound source in the scene. To address this, we introduce three key contributions. First, we propose a new training strategy that incorporates silence and noise, which improves performance in positive cases, while being more robust against negative sounds. Our resulting self-supervised model, SSL-SaN, achieves state-of-the-art performance compared to other self-supervised models, both in sound localization and cross-modal retrieval. Second, we propose a new metric that quantifies the trade-off between alignment and separability of auditory and visual features across positive and negative audio-visual pairs. Third, we present IS3+, an extended and improved version of the IS3 synthetic dataset with negative audio. Our data, metrics and code are available on the https://xavijuanola.github.io/SSL-SaN/.

The task of Visual Sound Source Localization (VSSL) involves identifying the location of sound sources in visual scenes, integrating audio-visual data for enhanced scene understanding. Despite advancements in state-of-the-art (SOTA) models, we observe three critical flaws: i) The evaluation of the models is mainly focused in sounds produced by objects that are visible in the image, ii) The evaluation often assumes a prior knowledge of the size of the sounding object, and iii) No universal threshold for localization in real-world scenarios is established, as previous approaches only consider positive examples without accounting for both positive and negative cases. In this paper, we introduce a novel test set and metrics designed to complete the current standard evaluation of VSSL models by testing them in scenarios where none of the objects in the image corresponds to the audio input, i.e. a negative audio. We consider three types of negative audio: silence, noise and offscreen. Our analysis reveals that numerous SOTA models fail to appropriately adjust their predictions based on audio input, suggesting that these models may not be leveraging audio information as intended. Additionally, we provide a comprehensive analysis of the range of maximum values in the estimated audio-visual similarity maps, in both positive and negative audio cases, and show that most of the models are not discriminative enough, making them unfit to choose a universal threshold appropriate to perform sound localization without any a priori information of the sounding object, that is, object size and visibility.

We introduce TalkVerse, a large-scale, open corpus for single-person, audio-driven talking video generation designed to enable fair, reproducible comparison across methods. While current state-of-the-art systems rely on closed data or compute-heavy models, TalkVerse offers 2.3 million high-resolution (720p/1080p) audio-video synchronized clips totaling 6.3k hours. These are curated from over 60k hours of video via a transparent pipeline that includes scene-cut detection, aesthetic assessment, strict audio-visual synchronization checks, and comprehensive annotations including 2D skeletons and structured visual/audio-style captions. Leveraging TalkVerse, we present a reproducible 5B DiT baseline built on Wan2.2-5B. By utilizing a video VAE with a high downsampling ratio and a sliding window mechanism with motion-frame context, our model achieves minute-long generation with low drift. It delivers comparable lip-sync and visual quality to the 14B Wan-S2V model but with 10times lower inference cost. To enhance storytelling in long videos, we integrate an MLLM director to rewrite prompts based on audio and visual cues. Furthermore, our model supports zero-shot video dubbing via controlled latent noise injection. We open-source the dataset, training recipes, and 5B checkpoints to lower barriers for research in audio-driven human video generation. Project Page: https://zhenzhiwang.github.io/talkverse/

We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single sound source; 2) fully-supervised audio-visual segmentation with multiple sound sources, and 3) fully-supervised audio-visual semantic segmentation. The first two settings need to generate binary masks of sounding objects indicating pixels corresponding to the audio, while the third setting further requires generating semantic maps indicating the object category. To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process. We also design a regularization loss to encourage audio-visual mapping during training. Quantitative and qualitative experiments on AVSBench compare our approach to several existing methods for related tasks, demonstrating that the proposed method is promising for building a bridge between the audio and pixel-wise visual semantics. Code is available at https://github.com/OpenNLPLab/AVSBench. Online benchmark is available at http://www.avlbench.opennlplab.cn.

Conventional voice conversion modifies voice characteristics from a source speaker to a target speaker, relying on audio input from both sides. However, this process becomes infeasible when clean audio is unavailable, such as in silent videos or noisy environments. In this work, we focus on the task of Silent Face-based Voice Conversion (SFVC), which does voice conversion entirely from visual inputs. i.e., given images of a target speaker and a silent video of a source speaker containing lip motion, SFVC generates speech aligning the identity of the target speaker while preserving the speech content in the source silent video. As this task requires generating intelligible speech and converting identity using only visual cues, it is particularly challenging. To address this, we introduce MuteSwap, a novel framework that employs contrastive learning to align cross-modality identities and minimize mutual information to separate shared visual features. Experimental results show that MuteSwap achieves impressive performance in both speech synthesis and identity conversion, especially under noisy conditions where methods dependent on audio input fail to produce intelligible results, demonstrating both the effectiveness of our training approach and the feasibility of SFVC.

We introduce EgoSonics, a method to generate semantically meaningful and synchronized audio tracks conditioned on silent egocentric videos. Generating audio for silent egocentric videos could open new applications in virtual reality, assistive technologies, or for augmenting existing datasets. Existing work has been limited to domains like speech, music, or impact sounds and cannot easily capture the broad range of audio frequencies found in egocentric videos. EgoSonics addresses these limitations by building on the strength of latent diffusion models for conditioned audio synthesis. We first encode and process audio and video data into a form that is suitable for generation. The encoded data is used to train our model to generate audio tracks that capture the semantics of the input video. Our proposed SyncroNet builds on top of ControlNet to provide control signals that enables temporal synchronization to the synthesized audio. Extensive evaluations show that our model outperforms existing work in audio quality, and in our newly proposed synchronization evaluation method. Furthermore, we demonstrate downstream applications of our model in improving video summarization.

We propose a novel step-by-step video-to-audio generation method that sequentially produces individual audio tracks, each corresponding to a specific sound event in the video. Our approach mirrors traditional Foley workflows, aiming to capture all sound events induced by a given video comprehensively. Each generation step is formulated as a guided video-to-audio synthesis task, conditioned on a target text prompt and previously generated audio tracks. This design is inspired by the idea of concept negation from prior compositional generation frameworks. To enable this guided generation, we introduce a training framework that leverages pre-trained video-to-audio models and eliminates the need for specialized paired datasets, allowing training on more accessible data. Experimental results demonstrate that our method generates multiple semantically distinct audio tracks for a single input video, leading to higher-quality composite audio synthesis than existing baselines.

Most lip-to-speech (LTS) synthesis models are trained and evaluated under the assumption that the audio-video pairs in the dataset are perfectly synchronized. In this work, we show that the commonly used audio-visual datasets, such as GRID, TCD-TIMIT, and Lip2Wav, can have data asynchrony issues. Training lip-to-speech with such datasets may further cause the model asynchrony issue -- that is, the generated speech and the input video are out of sync. To address these asynchrony issues, we propose a synchronized lip-to-speech (SLTS) model with an automatic synchronization mechanism (ASM) to correct data asynchrony and penalize model asynchrony. We further demonstrate the limitation of the commonly adopted evaluation metrics for LTS with asynchronous test data and introduce an audio alignment frontend before the metrics sensitive to time alignment for better evaluation. We compare our method with state-of-the-art approaches on conventional and time-aligned metrics to show the benefits of synchronization training.

Research on multi-modal contrastive learning strategies for audio and text has rapidly gained interest. Contrastively trained Audio-Language Models (ALMs), such as CLAP, which establish a unified representation across audio and language modalities, have enhanced the efficacy in various subsequent tasks by providing good text aligned audio encoders and vice versa. These improvements are evident in areas like zero-shot audio classification and audio retrieval, among others. However, the ability of these models to understand natural language and temporal relations is still a largely unexplored and open field for research. In this paper, we propose to equip the multi-modal ALMs with temporal understanding without loosing their inherent prior capabilities of audio-language tasks with a temporal instillation method TeminAL. We implement a two-stage training scheme TeminAL A & B, where the model first learns to differentiate between multiple sounds in TeminAL A, followed by a phase that instills a sense of time, thereby enhancing its temporal understanding in TeminAL B. This approach results in an average performance gain of 5.28% in temporal understanding on the ESC-50 dataset, while the model remains competitive in zero-shot retrieval and classification tasks on the AudioCap/Clotho datasets. We also note the lack of proper evaluation techniques for contrastive ALMs and propose a strategy for evaluating ALMs in zero-shot settings. The general-purpose zero-shot model evaluation strategy ZSTE, is used to evaluate various prior models. ZSTE demonstrates a general strategy to evaluate all ZS contrastive models. The model trained with TeminAL successfully outperforms current models on most downstream tasks.

We present VoiceShop, a novel speech-to-speech framework that can modify multiple attributes of speech, such as age, gender, accent, and speech style, in a single forward pass while preserving the input speaker's timbre. Previous works have been constrained to specialized models that can only edit these attributes individually and suffer from the following pitfalls: the magnitude of the conversion effect is weak, there is no zero-shot capability for out-of-distribution speakers, or the synthesized outputs exhibit undesirable timbre leakage. Our work proposes solutions for each of these issues in a simple modular framework based on a conditional diffusion backbone model with optional normalizing flow-based and sequence-to-sequence speaker attribute-editing modules, whose components can be combined or removed during inference to meet a wide array of tasks without additional model finetuning. Audio samples are available at https://voiceshopai.github.io.

While large audio-language models (LALMs) have demonstrated state-of-the-art audio understanding, their reasoning capability in complex soundscapes still falls behind large vision-language models (LVLMs). Compared to the visual domain, one bottleneck is the lack of large-scale chain-of-thought audio data to teach LALM stepwise reasoning. To circumvent this data and modality gap, we present SightSound-R1, a cross-modal distillation framework that transfers advanced reasoning from a stronger LVLM teacher to a weaker LALM student on the same audio-visual question answering (AVQA) dataset. SightSound-R1 consists of three core steps: (i) test-time scaling to generate audio-focused chains of thought (CoT) from an LVLM teacher, (ii) audio-grounded validation to filter hallucinations, and (iii) a distillation pipeline with supervised fine-tuning (SFT) followed by Group Relative Policy Optimization (GRPO) for the LALM student. Results show that SightSound-R1 improves LALM reasoning performance both in the in-domain AVQA test set as well as in unseen auditory scenes and questions, outperforming both pretrained and label-only distilled baselines. Thus, we conclude that vision reasoning can be effectively transferred to audio models and scaled with abundant audio-visual data.

Conventional hearing aids rely on fixed, frequency-dependent amplification and compression to manage reduced sensitivity, which often fails to provide sufficient listening support in complex environments, such as situations with multiple speakers (the ``cocktail party'' problem). To more comprehensively address the underlying encoding dysfunctions of hearing loss, we introduce the Differentiable Auditory Loop (DAL), a new open-source framework for personalized hearing aid design and fitting. Our first implementation of DAL incorporates CARFAC, a differentiable model of human cochlear function, which we ported to JAX, to optimize a deep neural network to match impaired auditory neural activity patterns with a normal-hearing reference. To build a hearing aid with the fine-grained spectro-temporal signal processing required, we adopt SEANet, a waveform-to-waveform fully convolutional UNet generator. We fine-tune the network by comparing the outputs of a CARFAC model fitted to normal hearing with that of a CARFAC model fitted to match each subject's individual hearing impairment. The comparison is done using loss functions derived from the respective CARFAC neural activity pattern (NAP) outputs and stabilized auditory images (SAIs), the latter providing a 2D representation that captures phase-insensitive temporal structure in the auditory nerve output. Through gradient descent, the SEANet model learns to both denoise the input and compensate for the hearing loss modelled by the impaired CARFAC model. Across neural-representation and signal-fidelity metrics, the DAL-optimized SEANet model outperformed the tested master hearing aid (MHA) baselines. The DAL framework provides a practical path toward model-based, machine-learning-driven personalization of hearing aid signal processing. Next steps include hardware deployment to enable real-world clinical testing.

As large language models become increasingly integrated into daily life, audio has emerged as a key interface for human-AI interaction. However, this convenience also introduces new vulnerabilities, making audio a potential attack surface for adversaries. Our research introduces WhisperInject, a two-stage adversarial audio attack framework that can manipulate state-of-the-art audio language models to generate harmful content. Our method uses imperceptible perturbations in audio inputs that remain benign to human listeners. The first stage uses a novel reward-based optimization method, Reinforcement Learning with Projected Gradient Descent (RL-PGD), to guide the target model to circumvent its own safety protocols and generate harmful native responses. This native harmful response then serves as the target for Stage 2, Payload Injection, where we use Projected Gradient Descent (PGD) to optimize subtle perturbations that are embedded into benign audio carriers, such as weather queries or greeting messages. Validated under the rigorous StrongREJECT, LlamaGuard, as well as Human Evaluation safety evaluation framework, our experiments demonstrate a success rate exceeding 86% across Qwen2.5-Omni-3B, Qwen2.5-Omni-7B, and Phi-4-Multimodal. Our work demonstrates a new class of practical, audio-native threats, moving beyond theoretical exploits to reveal a feasible and covert method for manipulating AI behavior.

Millions of people listen to podcasts, audio stories, and lectures, but editing speech remains tedious and time-consuming. Creators remove unnecessary words, cut tangential discussions, and even re-record speech to make recordings concise and engaging. Prior work automatically summarized speech by removing full sentences (extraction), but rigid extraction limits expressivity. AI tools can summarize then re-synthesize speech (abstraction), but abstraction strips the speaker's style. We present TalkLess, a system that flexibly combines extraction and abstraction to condense speech while preserving its content and style. To edit speech, TalkLess first generates possible transcript edits, selects edits to maximize compression, coverage, and audio quality, then uses a speech editing model to translate transcript edits into audio edits. TalkLess's interface provides creators control over automated edits by separating low-level wording edits (via the compression pane) from major content edits (via the outline pane). TalkLess achieves higher coverage and removes more speech errors than a state-of-the-art extractive approach. A comparison study (N=12) showed that TalkLess significantly decreased cognitive load and editing effort in speech editing. We further demonstrate TalkLess's potential in an exploratory study (N=3) where creators edited their own speech.

We present Kimi-Audio, an open-source audio foundation model that excels in audio understanding, generation, and conversation. We detail the practices in building Kimi-Audio, including model architecture, data curation, training recipe, inference deployment, and evaluation. Specifically, we leverage a 12.5Hz audio tokenizer, design a novel LLM-based architecture with continuous features as input and discrete tokens as output, and develop a chunk-wise streaming detokenizer based on flow matching. We curate a pre-training dataset that consists of more than 13 million hours of audio data covering a wide range of modalities including speech, sound, and music, and build a pipeline to construct high-quality and diverse post-training data. Initialized from a pre-trained LLM, Kimi-Audio is continual pre-trained on both audio and text data with several carefully designed tasks, and then fine-tuned to support a diverse of audio-related tasks. Extensive evaluation shows that Kimi-Audio achieves state-of-the-art performance on a range of audio benchmarks including speech recognition, audio understanding, audio question answering, and speech conversation. We release the codes, model checkpoints, as well as the evaluation toolkits in https://github.com/MoonshotAI/Kimi-Audio.

Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper presents StableAvatar, the first end-to-end video diffusion transformer that synthesizes infinite-length high-quality videos without post-processing. Conditioned on a reference image and audio, StableAvatar integrates tailored training and inference modules to enable infinite-length video generation. We observe that the main reason preventing existing models from generating long videos lies in their audio modeling. They typically rely on third-party off-the-shelf extractors to obtain audio embeddings, which are then directly injected into the diffusion model via cross-attention. Since current diffusion backbones lack any audio-related priors, this approach causes severe latent distribution error accumulation across video clips, leading the latent distribution of subsequent segments to drift away from the optimal distribution gradually. To address this, StableAvatar introduces a novel Time-step-aware Audio Adapter that prevents error accumulation via time-step-aware modulation. During inference, we propose a novel Audio Native Guidance Mechanism to further enhance the audio synchronization by leveraging the diffusion's own evolving joint audio-latent prediction as a dynamic guidance signal. To enhance the smoothness of the infinite-length videos, we introduce a Dynamic Weighted Sliding-window Strategy that fuses latent over time. Experiments on benchmarks show the effectiveness of StableAvatar both qualitatively and quantitatively.

Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS system trained only on the ASR corpora itself. ASR and TTS systems are built separately to show that text-only data can be used to enhance existing end-to-end ASR systems without the necessity of parameter or architecture changes. We compare our method with language model integration of the same text data and with simple data augmentation methods like SpecAugment and show that performance improvements are mostly independent. We achieve improvements of up to 33% relative in word-error-rate (WER) over a strong baseline with data-augmentation in a low-resource environment (LibriSpeech-100h), closing the gap to a comparable oracle experiment by more than 50\%. We also show improvements of up to 5% relative WER over our most recent ASR baseline on LibriSpeech-960h.

Live accompaniment models generate music for an incoming audio stream, committing to each output frame before hearing what comes next. In this strictly causal setting the model must infer tempo, meter, and metrical phase from its own imperfect past, whereby compounding errors quickly become audible as rhythmic drift. Put simply, the model has ears but no temporal reference, so when the ears hear imperfect, ambiguous music, the model will produce a flawed output. We propose Silent Metronome (SiMe), which gives it the temporal reference, encoding the phase within the beat and within the bar as periodic functions, pairing them with tempo and time signature, and supplying the result as a separate conditioning channel. Because this reference is independent of the generated audio, it cannot drift. Complementary auxiliary heads shape the latent representation, including a novel head that predicts the model's own future tokens. With the metrical signal taken from ground-truth annotations, beat alignment improves by a factor of 3.2 over the strictly causal baseline and surpasses a non-causal reference granted a full second of look-ahead. Coherence between input and accompaniment stays within a single point of that reference. These results suggest that streaming accompaniment systems should treat rhythm as a signal to be shared, as human ensembles do, rather than inferred.

General audio foundation models have recently achieved remarkable progress, enabling strong performance across diverse tasks. However, state-of-the-art models remain extremely large, often with hundreds of millions of parameters, leading to high inference costs and limited deployability on edge devices. Knowledge distillation is a proven strategy for model compression, but prior work in audio has mostly focused on supervised settings, relying on class logits, intermediate features, or architecture-specific techniques. Such assumptions exclude models that output only embeddings, such as self-supervised or metric-learning models. We introduce S-SONDO (Self-Supervised KnOwledge DistillatioN for General AuDio FOundation Models), the first framework to distill general audio models using only their output embeddings. By avoiding the need for logits or layer-level alignment, S-SONDO is architecture-agnostic and broadly applicable to embedding-based teachers. We demonstrate its effectiveness by distilling two audio foundation models into three efficient students that are up to 61 times smaller while retaining up to 96% of teacher performance. We also provide practical insights on loss choice and clustering-based balanced data sampling. Code is available here: https://github.com/MedAliAdlouni/ssondo.

Real-time streaming joint audio-video generation for character animation requires a generator to speak the requested transcript, maintain visual identity across chunks, and run within a strict playback budget. These requirements are difficult to satisfy simultaneously: chunk-wise autoregressive generation can accumulate transcript-audio misalignment and visual drift, while the few-step distillation needed for low latency often degrades spatial diversity and temporal quality. We present StreamChar, a streaming framework that separates long-horizon orchestration from short-window audio-video denoising. An LLM-based orchestrator uses the transcript and historical context to produce frame-aligned audio conditions, and a joint audio-video DiT performs local bidirectional denoising with reference and motion-frame conditioning. For efficient deployment, we use a two-stage distillation pipeline that first compresses the sampler and then fine-tunes the student under online chunk rollouts. A progress-aware pointer aligns partial transcripts with generated audio during rollout training, and a sink-chunk memory provides a persistent visual anchor for reducing long-horizon drift. Experiments on short-clip and long-horizon protocols show that StreamChar runs in real time on a single H100 GPU and provides a favorable system-level trade-off among transcript fidelity, audio-visual synchronization, visual quality, and streaming stability compared with recent joint and audio-driven baselines.

General audio comprehension now covers speech, sound, and music over durations from seconds to hours, driven by large audio-language models (LALMs) that are increasingly omni-modal. Yet the benchmarks that test them still rely on clips of seconds, where scores saturate and models converge; recent long-form efforts extend duration but evaluate long audio much as short clips are. We introduce AudioSpan, a benchmark that spans both duration and depth: it pairs audio from 10 minutes to over 2 hours with 3,240 questions across three cognitive levels, namely perception, understanding, and reasoning. Two paths supply the questions, differing in how question content is sourced and how ground truth is obtained. Native QA extracts questions from the audio's content, posing each as a multiple-choice item and an open-ended one graded by detailed rubrics. Anchor QA instead injects ground truth, planting acoustic anchors into the audio and building a perception-to-reasoning chain scored only to the first error. A fully automated pipeline constructs every item through structured captioning, QA generation, and adversarial critic feedback. Evaluating 12 LALMs on AudioSpan, we find the hard part comes before reasoning: distilling a few relevant facts from a long, redundant signal. This difficulty grows with audio length and falls hardest on perception, especially temporal grounding. AudioSpan is available at https://huggingface.co/datasets/holvan/AudioSpan.

Data-based and learning-based sound source localization (SSL) has shown promising results in challenging conditions, and is commonly set as a classification or a regression problem. Regression-based approaches have certain advantages over classification-based, such as continuous direction-of-arrival estimation of static and moving sources. However, multi-source scenarios require multiple regressors without a clear training strategy up-to-date, that does not rely on auxiliary information such as simultaneous sound classification. We investigate end-to-end training of such methods with a technique recently proposed for video object detectors, adapted to the SSL setting. A differentiable network is constructed that can be plugged to the output of the localizer to solve the optimal assignment between predictions and references, optimizing directly the popular CLEAR-MOT tracking metrics. Results indicate large improvements over directly optimizing mean squared errors, in terms of localization error, detection metrics, and tracking capabilities.

Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time applications. We propose OmniForcing, the first framework to distill an offline, dual-stream bidirectional diffusion model into a high-fidelity streaming autoregressive generator. However, naively applying causal distillation to such dual-stream architectures triggers severe training instability, due to the extreme temporal asymmetry between modalities and the resulting token sparsity. We address the inherent information density gap by introducing an Asymmetric Block-Causal Alignment with a zero-truncation Global Prefix that prevents multi-modal synchronization drift. The gradient explosion caused by extreme audio token sparsity during the causal shift is further resolved through an Audio Sink Token mechanism equipped with an Identity RoPE constraint. Finally, a Joint Self-Forcing Distillation paradigm enables the model to dynamically self-correct cumulative cross-modal errors from exposure bias during long rollouts. Empowered by a modality-independent rolling KV-cache inference scheme, OmniForcing achieves state-of-the-art streaming generation at sim25 FPS on a single GPU, maintaining multi-modal synchronization and visual quality on par with the bidirectional teacher.Project Page: https://omniforcing.com{https://omniforcing.com}

There has been a growing interest in the task of generating sound for silent videos, primarily because of its practicality in streamlining video post-production. However, existing methods for video-sound generation attempt to directly create sound from visual representations, which can be challenging due to the difficulty of aligning visual representations with audio representations. In this paper, we present SonicVisionLM, a novel framework aimed at generating a wide range of sound effects by leveraging vision-language models(VLMs). Instead of generating audio directly from video, we use the capabilities of powerful VLMs. When provided with a silent video, our approach first identifies events within the video using a VLM to suggest possible sounds that match the video content. This shift in approach transforms the challenging task of aligning image and audio into more well-studied sub-problems of aligning image-to-text and text-to-audio through the popular diffusion models. To improve the quality of audio recommendations with LLMs, we have collected an extensive dataset that maps text descriptions to specific sound effects and developed a time-controlled audio adapter. Our approach surpasses current state-of-the-art methods for converting video to audio, enhancing synchronization with the visuals, and improving alignment between audio and video components. Project page: https://yusiissy.github.io/SonicVisionLM.github.io/

A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representation between audio and language modalities have improved performance in many downstream applications, including zero-shot audio classification, audio retrieval, etc. However, the ability of these models to effectively perform compositional reasoning remains largely unexplored and necessitates additional research. In this paper, we propose CompA, a collection of two expert-annotated benchmarks with a majority of real-world audio samples, to evaluate compositional reasoning in ALMs. Our proposed CompA-order evaluates how well an ALM understands the order or occurrence of acoustic events in audio, and CompA-attribute evaluates attribute binding of acoustic events. An instance from either benchmark consists of two audio-caption pairs, where both audios have the same acoustic events but with different compositions. An ALM is evaluated on how well it matches the right audio to the right caption. Using this benchmark, we first show that current ALMs perform only marginally better than random chance, thereby struggling with compositional reasoning. Next, we propose CompA-CLAP, where we fine-tune CLAP using a novel learning method to improve its compositional reasoning abilities. To train CompA-CLAP, we first propose improvements to contrastive training with composition-aware hard negatives, allowing for more focused training. Next, we propose a novel modular contrastive loss that helps the model learn fine-grained compositional understanding and overcomes the acute scarcity of openly available compositional audios. CompA-CLAP significantly improves over all our baseline models on the CompA benchmark, indicating its superior compositional reasoning capabilities.

Cinematic audio source separation (CASS) is a fairly new subtask of audio source separation. A typical setup of CASS is a three-stem problem, with the aim of separating the mixture into the dialogue stem (DX), music stem (MX), and effects stem (FX). In practice, however, several edge cases exist as some sound sources do not fit neatly in either of these three stems, necessitating the use of additional auxiliary stems in production. One very common edge case is the singing voice in film audio, which may belong in either the DX or MX, depending heavily on the cinematic context. In this work, we demonstrate a very straightforward extension of the dedicated-decoder Bandit and query-based single-decoder Banquet models to a four-stem problem, treating non-musical dialogue, instrumental music, singing voice, and effects as separate stems. Interestingly, the query-based Banquet model outperformed the dedicated-decoder Bandit model. We hypothesized that this is due to a better feature alignment at the bottleneck as enforced by the band-agnostic FiLM layer. Dataset and model implementation will be made available at https://github.com/kwatcharasupat/source-separation-landing.

We propose DriftSE, a novel one-step generative framework for speech enhancement formulated as a latent distribution equilibrium problem. During training, the drifting field aligns the generator's pushforward distribution with the clean speech manifold through drifting in a latent domain. During inference, the drifting process is discarded, enabling one-step generation. We establish that its enhancement quality depends fundamentally on the choice of latent representation. Semantic latents preserve phonetic structure but fail to capture physical acoustic cues, whereas acoustic latents reconstruct the physical signal but risk linguistic hallucination. Therefore, we introduce dual-latent drifting, performing parallel drifting in both semantic and acoustic latents to simultaneously preserve phonetic intelligibility and acoustic fidelity. Additionally, we demonstrate that DriftSE enables fully unpaired training by aligning latent distributions rather than exact point-wise targets. Consequently, DriftSE facilitates cross-dataset learning in the absence of paired noisy-clean samples. Moreover, DriftSE exhibits broad architectural flexibility across different generator backbones. Extensive evaluations on additive denoising and convolutive dereverberation demonstrate robust one-step enhancement across both offline and real-time causal settings. Notably, DriftSE achieves state-of-the-art word error rates across all four evaluated datasets while strictly operating at 1 NFE. Code and audio examples are available online.

Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound separation has investigated separating a target sound out of an audio mixture given a text query. Such text-queried sound separation systems provide a natural and scalable interface for specifying arbitrary target sounds. However, supervised text-queried sound separation systems require costly labeled audio-text pairs for training. Moreover, the audio provided in existing datasets is often recorded in a controlled environment, causing a considerable generalization gap to noisy audio in the wild. In this work, we aim to approach text-queried universal sound separation by using only unlabeled data. We propose to leverage the visual modality as a bridge to learn the desired audio-textual correspondence. The proposed CLIPSep model first encodes the input query into a query vector using the contrastive language-image pretraining (CLIP) model, and the query vector is then used to condition an audio separation model to separate out the target sound. While the model is trained on image-audio pairs extracted from unlabeled videos, at test time we can instead query the model with text inputs in a zero-shot setting, thanks to the joint language-image embedding learned by the CLIP model. Further, videos in the wild often contain off-screen sounds and background noise that may hinder the model from learning the desired audio-textual correspondence. To address this problem, we further propose an approach called noise invariant training for training a query-based sound separation model on noisy data. Experimental results show that the proposed models successfully learn text-queried universal sound separation using only noisy unlabeled videos, even achieving competitive performance against a supervised model in some settings.

Full-duplex spoken language models can listen and speak simultaneously, enabling them to handle interruptions and backchannels in human conversation. However, text generation, speech synthesis, and audio playback proceed asynchronously. As a result, what a model believes it has said may not match what has actually been played to the user. We refer to the problem of recovering from an interruption while remaining aware of the model's realized speech as anchor interruption. To address this problem, we propose Self-Listening, a full-duplex modeling approach that interleaves user speech, model text, and the model's played speech. By feeding the realized speech output back to the model as an input stream, self-listening grounds interruption recovery in what the user has actually heard. We further introduce AnchorSpeech, a collection with homogeneous training and test splits for tracking which items of structured ordered responses have actually been spoken. AnchorSpeech-test evaluates whether a model can respond consistently with the last completed item before an interruption. Experiments show that, compared with full-duplex baselines, models equipped with self-listening mechanism achieve better anchoring performance.

We introduce BeepBank-500, a compact, fully synthetic earcon/alert dataset (300-500 clips) designed for rapid, rights-clean experimentation in human-computer interaction and audio machine learning. Each clip is generated from a parametric recipe controlling waveform family (sine, square, triangle, FM), fundamental frequency, duration, amplitude envelope, amplitude modulation (AM), and lightweight Schroeder-style reverberation. We use three reverberation settings: dry, and two synthetic rooms denoted 'rir small' ('small') and 'rir medium' ('medium') throughout the paper and in the metadata. We release mono 48 kHz WAV audio (16-bit), a rich metadata table (signal/spectral features), and tiny reproducible baselines for (i) waveform-family classification and (ii) f0 regression on single tones. The corpus targets tasks such as earcon classification, timbre analyses, and onset detection, with clearly stated licensing and limitations. Audio is dedicated to the public domain via CC0-1.0; code is under MIT. Data DOI: https://doi.org/10.5281/zenodo.17172015. Code: https://github.com/mandip42/earcons-mini-500.

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio poses unique challenges due to its inherently continuous nature. We research audio generation with a causal language model (LM) without discrete tokens. We leverage token-wise diffusion to model the continuous distribution of the next continuous-valued token. Our approach delivers significant improvements over previous discrete solution, AudioGen, achieving 20% and 40% relative gains on AudioCaps in Frechet Audio Distance (FAD) and Kullback-Leibler (KL) divergence, respectively. Additionally, we propose a novel masked next-token prediction task that incorporates masked prediction into the causal LM framework. On AudioCaps, the innovation yields 41% and 33% relative FAD improvements over AudioGen Base (285M) and AudioGen Large (1B) models, respectively, and is on par with the state-of-the-art (SOTA) diffusion models. Furthermore, we achieve these results with significantly fewer parameters -- 193M for our Base and 462M for our Large models.

Video and audio are closely correlated modalities that humans naturally perceive together. While recent advancements have enabled the generation of audio or video from text, producing both modalities simultaneously still typically relies on either a cascaded process or multi-modal contrastive encoders. These approaches, however, often lead to suboptimal results due to inherent information losses during inference and conditioning. In this paper, we introduce SyncFlow, a system that is capable of simultaneously generating temporally synchronized audio and video from text. The core of SyncFlow is the proposed dual-diffusion-transformer (d-DiT) architecture, which enables joint video and audio modelling with proper information fusion. To efficiently manage the computational cost of joint audio and video modelling, SyncFlow utilizes a multi-stage training strategy that separates video and audio learning before joint fine-tuning. Our empirical evaluations demonstrate that SyncFlow produces audio and video outputs that are more correlated than baseline methods with significantly enhanced audio quality and audio-visual correspondence. Moreover, we demonstrate strong zero-shot capabilities of SyncFlow, including zero-shot video-to-audio generation and adaptation to novel video resolutions without further training.

Despite recent progress in large-scale sound event detection (SED) systems capable of handling hundreds of sound classes, existing multi-class classification frameworks remain fundamentally limited. They cannot process free-text sound queries, which enable more flexible and user-friendly interaction, and they lack zero-shot capabilities and offer poor few-shot adaptability. Although text-query-based separation methods have been explored, they primarily focus on source separation and are ill-suited for SED tasks that require precise temporal localization and efficient detection across large and diverse sound vocabularies. In this paper, we propose FlexSED, an open-vocabulary sound event detection system. FlexSED builds on a pretrained audio SSL model and the CLAP text encoder, introducing an encoder-decoder composition and an adaptive fusion strategy to enable effective continuous training from pretrained weights. To ensure robust supervision, it also employs large language models (LLMs) to assist in event query selection during training, addressing challenges related to missing labels. As a result, FlexSED achieves superior performance compared to vanilla SED models on AudioSet-Strong, while demonstrating strong zero-shot and few-shot capabilities. We release the code and pretrained models to support future research and applications based on FlexSED.

Audio-language models (ALMs) can exploit textual shortcuts to answer questions while overlooking acoustic evidence, weakening audio understanding. On-policy distillation (OPD) trains compact ALMs by supervising student-generated responses with teacher predictions, but does not explicitly distinguish acoustic support from linguistic predictability. We propose Reward-Tilted On-Policy Distillation (RT-OPD) to strengthen acoustic grounding. Given the same question and student-generated text, a frozen teacher predicts the next token with and without audio inputs. Their log-probability contrast defines a reward that reshapes the teacher distribution for reverse-KL distillation, emphasizing the additional evidence provided by audio. Across two compact students and three benchmarks, RT-OPD consistently outperforms Vanilla OPD. Experiments with silenced and replacement audio further suggest that RT-OPD strengthens the student's reliance on acoustic evidence. Our 3B model achieves 72.72% accuracy on MMAU, the highest among the compared 3B models and competitive with several 7B and 8B models. Code and model checkpoints are available at https://github.com/KaiyangLi1992/RT-OPD.

Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within a single model. However, existing controllable generation frameworks are typically restricted to video-only control. This restricts comprehensive controllability and often leads to suboptimal cross-modal alignment. To bridge this gap, we present MMControl, which enables users to perform Multi-Modal Control in joint audio-video generation. MMControl introduces a dual-stream conditional injection mechanism. It incorporates both visual and acoustic control signals, including reference images, reference audio, depth maps, and pose sequences, into a joint generation process. These conditions are injected through bypass branches into a joint audio-video Diffusion Transformer, enabling the model to simultaneously generate identity-consistent video and timbre-consistent audio under structural constraints. Furthermore, we introduce modality-specific guidance scaling, which allows users to independently and dynamically adjust the influence strength of each visual and acoustic condition at inference time. Extensive experiments demonstrate that MMControl achieves fine-grained, composable control over character identity, voice timbre, body pose, and scene layout in joint audio-video generation.

Joint audio-video generation aims to synthesize temporally synchronized and semantically coherent visual-acoustic content. However, existing open-source methods mainly rely on either dual-tower designs with posterior alignment or fully unified tri-modal designs that mix textual context, audio and video in one shared space. The former weakens fine-grained audio-video co-evolution, while the latter couples semantic conditioning with low-level synchronization. To address these limitations, we propose NAVA, a Native Audio-Visual Alignment framework for joint audio-video generation. NAVA is built upon context-conditioned native audio-visual alignment: it first establishes audio-video correspondence in a dedicated interaction space, and then uses external context to condition the joint denoising process. Specifically, NAVA is instantiated with an Align-then-Fuse MMDiT architecture, which transitions from modality-aware audio-video alignment to modality-shared joint denoising. Furthermore, we introduce Timbre-in-Context Conditioning to associate reference timbre cues with corresponding speech spans to achieve controllable speech timbre. Experiments on Verse-Bench and Seed-TTS, together with a user study, demonstrate that NAVA achieves superior video quality, precise audio-visual synchronization, competitive audio quality, and stronger reference-timbre controllability using only 6.3B parameters.

Component-level audio Spoofing (Comp-Spoof) targets a new form of audio manipulation where only specific components of a signal, such as speech or environmental sound, are forged or substituted while other components remain genuine. Existing anti-spoofing datasets and methods treat an utterance or a segment as entirely bona fide or entirely spoofed, and thus cannot accurately detect component-level spoofing. To address this, we construct a new dataset, CompSpoof, covering multiple combinations of bona fide and spoofed speech and environmental sound. We further propose a separation-enhanced joint learning framework that separates audio components apart and applies anti-spoofing models to each one. Joint learning is employed, preserving information relevant for detection. Extensive experiments demonstrate that our method outperforms the baseline, highlighting the necessity of separate components and the importance of detecting spoofing for each component separately. Datasets and code are available at: https://github.com/XuepingZhang/CompSpoof.

Historical films suffer from co-occurring visual and audio degradations---blur, noise, flicker, hiss, clipping, and dropout---yet existing methods restore each modality independently, leaving quality gaps and cross-modal inconsistency. We present OmniVR, the first joint audio-video generative restoration model. Built upon a 22B-parameter audio-video generation backbone, OmniVR formulates restoration as conditional generation within a unified multimodal DiT: the low-quality video and audio are encoded as latent conditions, combined with a fixed restoration prompt, and jointly denoised to recover visual structure, temporal motion, and acoustic detail under one coordinated objective. Three key designs enable this adaptation: (1) a joint audio-video degradation pipeline that simulates real old-film characteristics from Internet-collected data; (2) an architecture-preserving text-to-audio-video (T2AV) to audio-video-to-audio-video (AV2AV) transition with prompt annealing that maximally retains the generative prior; and (3) first-frame image-to-video (I2V) anchoring with loss reweighting and waveform supervision for long-video extrapolation and audio fidelity. We also propose OmniVRBench, the first benchmark that evaluates audio-video restoration across visual quality, audio quality, temporal consistency, and audio-visual synchrony on 200 real historical clips. OmniVR surpasses all prior methods on all six visual metrics, achieves the best audio quality, and produces natural colorization---the first method to jointly address all three aspects. Code and weights will be publicly released. Project Page: https://xin1u.github.io/OminiVR_PAGE/

Large Audio Language Models (LALMs) still struggle in complex acoustic scenes because they often fail to preserve task-relevant acoustic evidence before reasoning begins. We call this failure the evidence bottleneck: state-of-the-art systems show larger deficits in evidence extraction than in downstream reasoning, suggesting that the main limitation lies in upstream perception rather than reasoning policy. To address this problem, we propose EvA (Evidence-First Audio), a dual-path architecture that combines Whisper and CED-Base through non-compressive, time-aligned fusion. EvA first aggregates intermediate CED layers to preserve multi-scale acoustic cues, then aligns the aggregated CED features to the Whisper timeline and adds the two streams without changing sequence length. We also build EvA-Perception, a large-scale open-source training set with about 54K event-ordered captions (150 h) and about 500K QA pairs. Under a unified zero-shot protocol, EvA achieves the best open-source Perception scores on MMAU, MMAR, and MMSU, and improves over Kimi-Audio-7B on all reported metrics, with the largest gains on perception-heavy splits. These results support the evidence-first hypothesis: stronger audio understanding depends on preserving acoustic evidence before reasoning.

Video-to-audio generation (V2A) is of increasing importance in domains such as film post-production, AR/VR, and sound design, particularly for the creation of Foley sound effects synchronized with on-screen actions. Foley requires generating audio that is both semantically aligned with visible events and temporally aligned with their timing. Yet, there is a mismatch between evaluation and downstream applications due to the absence of a benchmark tailored to Foley-style scenarios. We find that 74% of videos from past evaluation datasets have poor audio-visual correspondence. Moreover, they are dominated by speech and music, domains that lie outside the use case for Foley. To address this gap, we introduce FoleyBench, the first large-scale benchmark explicitly designed for Foley-style V2A evaluation. FoleyBench contains 5,000 (video, ground-truth audio, text caption) triplets, each featuring visible sound sources with audio causally tied to on-screen events. The dataset is built using an automated, scalable pipeline applied to in-the-wild internet videos from YouTube-based and Vimeo-based sources. Compared to past datasets, we show that videos from FoleyBench have stronger coverage of sound categories from a taxonomy specifically designed for Foley sound. Each clip is further labeled with metadata capturing source complexity, UCS/AudioSet category, and video length, enabling fine-grained analysis of model performance and failure modes. We benchmark several state-of-the-art V2A models, evaluating them on audio quality, audio-video alignment, temporal synchronization, and audio-text consistency. Samples are available at: https://gclef-cmu.org/foleybench

This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian white noise signal and iteratively refines the signal via a gradient-based sampler conditioned on the mel-spectrogram. WaveGrad offers a natural way to trade inference speed for sample quality by adjusting the number of refinement steps, and bridges the gap between non-autoregressive and autoregressive models in terms of audio quality. We find that it can generate high fidelity audio samples using as few as six iterations. Experiments reveal WaveGrad to generate high fidelity audio, outperforming adversarial non-autoregressive baselines and matching a strong likelihood-based autoregressive baseline using fewer sequential operations. Audio samples are available at https://wavegrad.github.io/.

Recent advancements in deep learning have led to widespread use of techniques for audio content generation, notably employing Denoising Diffusion Probabilistic Models (DDPM) across various tasks. Among these, Foley Sound Synthesis is of particular interest for its role in applications for the creation of multimedia content. Given the temporal-dependent nature of sound, it is crucial to design generative models that can effectively handle the sequential modeling of audio samples. Selective State Space Models (SSMs) have recently been proposed as a valid alternative to previously proposed techniques, demonstrating competitive performance with lower computational complexity. In this paper, we introduce MambaFoley, a diffusion-based model that, to the best of our knowledge, is the first to leverage the recently proposed SSM known as Mamba for the Foley sound generation task. To evaluate the effectiveness of the proposed method, we compare it with a state-of-the-art Foley sound generative model using both objective and subjective analyses.

Modern multimodal large language models often claim "video understanding," yet most evaluations use muted videos or simply discard audio. We ask a direct question: how much does audio actually matter for contemporary Video-LLMs and the benchmarks that certify them? We audit widely used suites and observe that many items are even solvable from a single frame, rendering audio largely redundant. Building on LLaVA-OneVision architecture, we attach a speech/audio encoder (e.g., Whisper) and analyze when audio helps, while addressing audio token explosion with a lightweight Mamba-based state-space token compressor. We find that audio yields minimal gains on recent video benchmarks but is decisive on curated, audio-sensitive subsets. To enable faithful evaluation, we release AVQA-Hard and Music-AVQA-Hard, our model, and code. Our findings surface a growing gap between current academic practice and real-world expectations, and provide practical tools for scalable audio-visual Video-LLMs. We will fully open-source our work at https://github.com/naver-ai/LLaVA-AV-SSM.

Text-to-audio systems, while increasingly performant, are slow at inference time, thus making their latency unpractical for many creative applications. We present Adversarial Relativistic-Contrastive (ARC) post-training, the first adversarial acceleration algorithm for diffusion/flow models not based on distillation. While past adversarial post-training methods have struggled to compare against their expensive distillation counterparts, ARC post-training is a simple procedure that (1) extends a recent relativistic adversarial formulation to diffusion/flow post-training and (2) combines it with a novel contrastive discriminator objective to encourage better prompt adherence. We pair ARC post-training with a number optimizations to Stable Audio Open and build a model capable of generating approx12s of 44.1kHz stereo audio in approx75ms on an H100, and approx7s on a mobile edge-device, the fastest text-to-audio model to our knowledge.

Multimodal generative models have shown impressive advances with the help of powerful diffusion models. Despite the progress, generating sound solely from text poses challenges in ensuring comprehensive scene depiction and temporal alignment. Meanwhile, video-to-sound generation limits the flexibility to prioritize sound synthesis for specific objects within the scene. To tackle these challenges, we propose a novel video-and-text-to-sound generation method, called ReWaS, where video serves as a conditional control for a text-to-audio generation model. Our method estimates the structural information of audio (namely, energy) from the video while receiving key content cues from a user prompt. We employ a well-performing text-to-sound model to consolidate the video control, which is much more efficient for training multimodal diffusion models with massive triplet-paired (audio-video-text) data. In addition, by separating the generative components of audio, it becomes a more flexible system that allows users to freely adjust the energy, surrounding environment, and primary sound source according to their preferences. Experimental results demonstrate that our method shows superiority in terms of quality, controllability, and training efficiency. Our demo is available at https://naver-ai.github.io/rewas

Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A), and joint video-text-to-audio (VT2A) generation offers significant application flexibility, yet faces two unexplored foundational challenges: (1) the scarcity of high-quality audio captions with tight A-V-T alignment, leading to severe semantic conflict between multimodal conditions, and (2) cross-task and intra-task competition, manifesting as an adverse V2A-T2A performance trade-off and modality bias in the VT2A task. First, to address data scarcity, we introduce SoundAtlas, a large-scale dataset (470k pairs) that significantly outperforms existing benchmarks and even human experts in quality. Powered by a novel agentic pipeline, it integrates Vision-to-Language Compression to mitigate visual bias of MLLMs, a Junior-Senior Agent Handoff for a 5 times cost reduction, and rigorous Post-hoc Filtering to ensure fidelity. Consequently, SoundAtlas delivers semantically rich and temporally detailed captions with tight V-A-T alignment. Second, we propose Omni2Sound, a unified VT2A diffusion model supporting flexible input modalities. To resolve the inherent cross-task and intra-task competition, we design a three-stage multi-task progressive training schedule that converts cross-task competition into joint optimization and mitigates modality bias in the VT2A task, maintaining both audio-visual alignment and off-screen audio generation faithfulness. Finally, we construct VGGSound-Omni, a comprehensive benchmark for unified evaluation, including challenging off-screen tracks. With a standard DiT backbone, Omni2Sound achieves unified SOTA performance across all three tasks within a single model, demonstrating strong generalization across benchmarks with heterogeneous input conditions. The project page is at https://swapforward.github.io/Omni2Sound.

Zero-shot voice conversion (VC) aims to convert a source utterance into the voice of an unseen target speaker while preserving its linguistic content. Although recent systems have improved conversion quality, building zero-shot VC systems for interactive scenarios remains challenging because high-fidelity speaker transfer and low-latency streaming inference are difficult to achieve simultaneously. In this work, we present X-VC, a zero-shot streaming VC system that performs one-step conversion in the latent space of a pretrained neural codec. X-VC uses a dual-conditioning acoustic converter that jointly models source codec latents and frame-level acoustic conditions derived from target reference speech, while injecting utterance-level target speaker information through adaptive normalization. To reduce the mismatch between training and inference, we train the model with generated paired data and a role-assignment strategy that combines standard, reconstruction, and reversed modes. For streaming inference, we further adopt a chunkwise inference scheme with overlap smoothing that is aligned with the segment-based training paradigm of the codec. Experiments on Seed-TTS-Eval show that X-VC achieves the best streaming WER in both English and Chinese, strong speaker similarity in same-language and cross-lingual settings, and substantially lower offline real-time factor than the compared baselines. These results suggest that codec-space one-step conversion is a practical approach for building high-quality low-latency zero-shot VC systems. Audio samples are available at https://x-vc.github.io. Our code and checkpoints will also be released.

Real-world speech recordings suffer from degradations such as background noise and reverberation. Speech enhancement aims to mitigate these issues by generating clean high-fidelity signals. While recent generative approaches for speech enhancement have shown promising results, they still face two major challenges: (1) content hallucination, where plausible phonemes generated differ from the original utterance; and (2) inconsistency, failing to preserve speaker's identity and paralinguistic features from the input speech. In this work, we introduce DiTSE (Diffusion Transformer for Speech Enhancement), which addresses quality issues of degraded speech in full bandwidth. Our approach employs a latent diffusion transformer model together with robust conditioning features, effectively addressing these challenges while remaining computationally efficient. Experimental results from both subjective and objective evaluations demonstrate that DiTSE achieves state-of-the-art audio quality that, for the first time, matches real studio-quality audio from the DAPS dataset. Furthermore, DiTSE significantly improves the preservation of speaker identity and content fidelity, reducing hallucinations across datasets compared to state-of-the-art enhancers. Audio samples are available at: http://hguimaraes.me/DiTSE

Traditional speech systems typically rely on separate, task-specific models for text-to-speech (TTS), automatic speech recognition (ASR), and voice conversion (VC), resulting in fragmented pipelines that limit scalability, efficiency, and cross-task generalization. In this paper, we present General-Purpose Audio (GPA), a unified audio foundation model that integrates multiple core speech tasks within a single large language model (LLM) architecture. GPA operates on a shared discrete audio token space and supports instruction-driven task induction, enabling a single autoregressive model to flexibly perform TTS, ASR, and VC without architectural modifications. This unified design combines a fully autoregressive formulation over discrete speech tokens, joint multi-task training across speech domains, and a scalable inference pipeline that achieves high concurrency and throughput. The resulting model family supports efficient multi-scale deployment, including a lightweight 0.3B-parameter variant optimized for edge and resource-constrained environments. Together, these design choices demonstrate that a unified autoregressive architecture can achieve competitive performance across diverse speech tasks while remaining viable for low-latency, practical deployment.

We introduce Audio-SDS, a generalization of Score Distillation Sampling (SDS) to text-conditioned audio diffusion models. While SDS was initially designed for text-to-3D generation using image diffusion, its core idea of distilling a powerful generative prior into a separate parametric representation extends to the audio domain. Leveraging a single pretrained model, Audio-SDS enables a broad range of tasks without requiring specialized datasets. In particular, we demonstrate how Audio-SDS can guide physically informed impact sound simulations, calibrate FM-synthesis parameters, and perform prompt-specified source separation. Our findings illustrate the versatility of distillation-based methods across modalities and establish a robust foundation for future work using generative priors in audio tasks.

Text-to-video (T2V) diffusion models have recently achieved impressive visual quality, yet most systems still generate silent clips and treat audio as a secondary concern. Existing audio-video generation pipelines typically decompose the task into cascaded stages, which accumulate errors across modalities and are trained under separate objectives. Recent joint audio-video generators alleviate this issue but often rely on dual-tower architectures with ad-hoc cross-modal bridges and static, single-shot text conditioning, making it difficult to both reuse T2V backbones and to reason about how audio, video and language interact over time. To address these challenges, we propose 3MDiT, a unified tri-modal diffusion transformer for text-driven synchronized audio-video generation. Our framework models video, audio and text as jointly evolving streams: an isomorphic audio branch mirrors a T2V backbone, tri-modal omni-blocks perform feature-level fusion across the three modalities, and an optional dynamic text conditioning mechanism updates the text representation as audio and video evidence co-evolve. The design supports two regimes: training from scratch on audio-video data, and orthogonally adapting a pretrained T2V model without modifying its backbone. Experiments show that our approach generates high-quality videos and realistic audio while consistently improving audio-video synchronization and tri-modal alignment across a range of quantitative metrics.

Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single task such as streaming ASR or voice chatting. It is time to unify them into one online LALM: a model that, through an always-on perceive-decide-respond loop, listens to sound, environment, and instructions in real time and reacts on the fly. We formalize this regime as the Audio Interaction Model, and realize it with Audio-Interaction, a unified streaming model that retains offline task execution while adding online general audio instruction following, from dialogue to full voice chatting, deciding when to respond from the semantics of the stream. To enable this, we propose SoundFlow, a framework that instantiates the perceive-decide-respond loop end to end, from data to training to deployment, through streaming-native data construction, comprehension-aware training, and asynchronous low-latency inference for stable real-time interaction. We further construct StreamAudio-2M, a 2.6M-item streaming corpus spanning 7 fundamental abilities and 28 sub-tasks, and Proactive-Sound-Bench for evaluating proactive audio intervention. Across 8 benchmarks, Audio-Interaction preserves competitive performance on mainstream audio tasks while unlocking capabilities inaccessible to offline LALMs, including real-time ASR, streaming audio instruction following, and proactive help.

Text-to-audio grounding (TAG) task aims to predict the onsets and offsets of sound events described by natural language. This task can facilitate applications such as multimodal information retrieval. This paper focuses on weakly-supervised text-to-audio grounding (WSTAG), where frame-level annotations of sound events are unavailable, and only the caption of a whole audio clip can be utilized for training. WSTAG is superior to strongly-supervised approaches in its scalability to large audio-text datasets. Two WSTAG frameworks are studied in this paper: sentence-level and phrase-level. First, we analyze the limitations of mean pooling used in the previous WSTAG approach and investigate the effects of different pooling strategies. We then propose phrase-level WSTAG to use matching labels between audio clips and phrases for training. Advanced negative sampling strategies and self-supervision are proposed to enhance the accuracy of the weak labels and provide pseudo strong labels. Experimental results show that our system significantly outperforms the previous WSTAG SOTA. Finally, we conduct extensive experiments to analyze the effects of several factors on phrase-level WSTAG. The code and model is available at https://github.com/wsntxxn/TextToAudioGrounding.

This paper introduces V2A-DPO, a novel Direct Preference Optimization (DPO) framework tailored for flow-based video-to-audio generation (V2A) models, incorporating key adaptations to effectively align generated audio with human preferences. Our approach incorporates three core innovations: (1) AudioScore-a comprehensive human preference-aligned scoring system for assessing semantic consistency, temporal alignment, and perceptual quality of synthesized audio; (2) an automated AudioScore-driven pipeline for generating large-scale preference pair data for DPO optimization; (3) a curriculum learning-empowered DPO optimization strategy specifically tailored for flow-based generative models. Experiments on benchmark VGGSound dataset demonstrate that human-preference aligned Frieren and MMAudio using V2A-DPO outperform their counterparts optimized using Denoising Diffusion Policy Optimization (DDPO) as well as pre-trained baselines. Furthermore, our DPO-optimized MMAudio achieves state-of-the-art performance across multiple metrics, surpassing published V2A models.

Text-to-spatial audio generation, such as text-to-First-Order Ambisonics (FOA), provides a convenient way to create spatial audio for billion-dollar gaming and film industries. However, existing text-to-FOA methods are largely data-driven and may produce audio that violates acoustic relations between source direction and distance. They also separate descriptive and parametric control, forcing users to trade usability for precision. In this paper, we present PhysWave, a physics-guided latent diffusion model for controllable text-to-FOA generation. PhysWave unifies natural-language and trajectory control through a shared waypoint-caption representation, and augments diffusion training with two differentiable acoustic priors: spherical-harmonic direction consistency and inverse-square distance consistency. To support dynamic spatial generation, we further construct a 300K-clip FOA dataset with diverse sound categories and source trajectories. Extensive results show that the proposed priors help PhysWave generate spatially consistent FOA audio while maintaining competitive audio quality. Further analyses show that these physics priors improve spatial consistency during training and can also be used as inference-time guidance for training-free spatial refinement.

The goal of this paper is to provide a new perspective on audio-visual target speaker extraction (AV-TSE) by decoupling the separation and target selection. Conventional AV-TSE systems typically integrate audio and visual features deeply to re-learn the entire separation process, which can act as a fidelity ceiling due to the noisy nature of in-the-wild audio-visual datasets. To address this, we propose Plug-and-Steer, which assigns high-fidelity separation to a frozen audio-only backbone and limits the role of visual modality strictly to target selection. We introduce the Latent Steering Matrix (LSM), a minimalist linear transformation that re-routes latent features within the backbone to anchor the target speaker to a designated channel. Experiments across four representative architectures show that our method effectively preserves the acoustic priors of diverse backbones, achieving perceptual quality comparable to the original backbones. Audio samples are available at: https://plugandsteer.github.io

Propelled by the breakthrough in deep generative models, audio-to-image generation has emerged as a pivotal cross-model task that converts complex auditory signals into rich visual representations. However, previous works only focus on single-source audio inputs for image generation, ignoring the multi-source characteristic in natural auditory scenes, thus limiting the performance in generating comprehensive visual content. To bridge this gap, a method called MACS is proposed to conduct multi-source audio-to-image generation. This is the first work that explicitly separates multi-source audio to capture the rich audio components before image generation. MACS is a two-stage method. In the first stage, multi-source audio inputs are separated by a weakly supervised method, where the audio and text labels are semantically aligned by casting into a common space using the large pre-trained CLAP model. We introduce a ranking loss to consider the contextual significance of the separated audio signals. In the second stage, efficient image generation is achieved by mapping the separated audio signals to the generation condition using only a trainable adapter and a MLP layer. We preprocess the LLP dataset as the first full multi-source audio-to-image generation benchmark. The experiments are conducted on multi-source, mixed-source, and single-source audio-to-image generation tasks. The proposed MACS outperforms the current state-of-the-art methods in 17 of the 21 evaluation indexes on all tasks and delivers superior visual quality. The code will be publicly available.

Recent work has studied text-to-audio synthesis using large amounts of paired text-audio data. However, audio recordings with high-quality text annotations can be difficult to acquire. In this work, we approach text-to-audio synthesis using unlabeled videos and pretrained language-vision models. We propose to learn the desired text-audio correspondence by leveraging the visual modality as a bridge. We train a conditional diffusion model to generate the audio track of a video, given a video frame encoded by a pretrained contrastive language-image pretraining (CLIP) model. At test time, we first explore performing a zero-shot modality transfer and condition the diffusion model with a CLIP-encoded text query. However, we observe a noticeable performance drop with respect to image queries. To close this gap, we further adopt a pretrained diffusion prior model to generate a CLIP image embedding given a CLIP text embedding. Our results show the effectiveness of the proposed method, and that the pretrained diffusion prior can reduce the modality transfer gap. While we focus on text-to-audio synthesis, the proposed model can also generate audio from image queries, and it shows competitive performance against a state-of-the-art image-to-audio synthesis model in a subjective listening test. This study offers a new direction of approaching text-to-audio synthesis that leverages the naturally-occurring audio-visual correspondence in videos and the power of pretrained language-vision models.