Authors

Venue

Date

Share

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

Ho Kei Cheng

Masato Ishii

Akio Hayakawa

Takashi Shibuya

Alexander Schwing

Yuki Mitsufuji

CVPR-25

2025

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.

Related Publications

Music Arena: Live Evaluation for Text-to-Music

NeurIPS, 2025
Yonghyun Kim, Wayne Chi, Anastasios N. Angelopoulos, Wei-Lin Chiang, Koichi Saito, Shinji Watanabe, Yuki Mitsufuji, Chris Donahue

We present Music Arena, an open platform for scalable human preference evaluation of text-to-music (TTM) models. Soliciting human preferences via listening studies is the gold standard for evaluation in TTM, but these studies are expensive to conduct and difficult to compare…

Large-Scale Training Data Attribution for Music Generative Models via Unlearning

NeurIPS, 2025
Woosung Choi, Junghyun Koo*, Kin Wai Cheuk, Joan Serrà, Marco A. Martínez-Ramírez, Yukara Ikemiya, Naoki Murata, Yuhta Takida, Wei-Hsiang Liao, Yuki Mitsufuji

This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed to the generation of a particular output from a specific mod…

Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion

NeurIPS, 2025
Michail Dontas, Yutong He, Naoki Murata, Yuki Mitsufuji, J. Zico Kolter*, Ruslan Salakhutdinov*

Blind inverse problems, where both the target data and forward operator are unknown, are crucial to many computer vision applications. Existing methods often depend on restrictive assumptions such as additional training, operator linearity, or narrow image distributions, thu…

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

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.