Pith. sign in

REVIEW 7 cited by

MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.15322 v2 pith:LJREVEYH submitted 2024-12-19 cs.CV cs.LGcs.SDeess.AS

classification cs.CVcs.LGcs.SDeess.AS
keywords mmaudioaudiotraininghigh-qualityjointvideoachievesaudio-visual
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio. In contrast to single-modality training conditioned on (limited) video data only, MMAudio is jointly trained with larger-scale, readily available text-audio data to learn to generate semantically aligned high-quality audio samples. Additionally, we improve audio-visual synchrony with a conditional synchronization module that aligns video conditions with audio latents at the frame level. Trained with a flow matching objective, MMAudio achieves new video-to-audio state-of-the-art among public models in terms of audio quality, semantic alignment, and audio-visual synchronization, while having a low inference time (1.23s to generate an 8s clip) and just 157M parameters. MMAudio also achieves surprisingly competitive performance in text-to-audio generation, showing that joint training does not hinder single-modality performance. Code and demo are available at: https://hkchengrex.github.io/MMAudio

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SynSFX: Multi-Model Sound Effects Synthesis Dataset for Deepfake Detection and Evaluation

    cs.SD 2026-07 conditional novelty 6.0 of 10

    SynSFX provides a multi-generator sound-effect deepfake corpus showing speech detectors fail, joint training mitigates forgetting, but generalization to unseen generators remains poor due to artifact overfitting.

  2. DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis

    cs.MM 2025-07 conditional novelty 6.0 of 10

    A single multimodal language model can generate intelligible speech and synchronized background audio jointly from a silent video, transcript, and reference voice, outperforming separately concatenated speech and audi...

  3. Sounding that Object: Interactive Object-Aware Image to Audio Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A latent diffusion audio model is trained to ground sound in image patches, then uses SAM segmentation masks at test time so users can generate audio for selected objects in a scene.

  4. AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation

    cs.SD 2025-05 conditional novelty 6.0 of 10

    A training-free multi-agent framework that decomposes multimodal inputs into audio events, selects specialized generators, and self-corrects outputs to produce multiple audio types.

  5. SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet

    cs.SD 2025-05 conditional novelty 6.0 of 10

    A ControlNet branch plus a frequency-aware feature aligner lets a pretrained masked generative TTA model produce video-synchronized foley, beating several from-scratch models on VGGSound.

  6. KVAE: Family of Tokenizers for Multimodal Generative Models

    cs.CV 2026-08 conditional novelty 5.0 of 10

    KVAE introduces image, video, and full-band audio tokenizers whose reconstruction and downstream generation quality is competitive with, and often better than, current open-source tokenizers in head-to-head tests.

  7. Towards Video to Piano Music Generation with Chain-of-Perform Support Benchmarks

    cs.SD 2025-05 reject novelty 4.0 of 10

    The paper proposes an open-source 10-hour video-to-piano benchmark with four-level Chain-of-Perform annotations, but supplies only preliminary, incomplete baseline results.

Pith tools