{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/taming-multimodal-joint-training-for-high","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","arxiv_id":"2412.15322","date":"2024-12-19","proceeding":"CVPR 2025 1","authors":["Ho Kei Cheng","Masato Ishii","Akio Hayakawa","Takashi Shibuya","Alexander Schwing","Yuki Mitsufuji"],"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","url_abs":"https://arxiv.org/abs/2412.15322v2","url_pdf":"https://arxiv.org/pdf/2412.15322v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"taming-multimodal-joint-training-for-high","repo_url":"https://github.com/hkchengrex/MMAudio","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"audio-synthesis","task_name":"Audio Synthesis"},{"task_slug":"audio-visual-synchronization","task_name":"Audio-Visual Synchronization"},{"task_slug":"video-to-sound-generation","task_name":"Video-to-Sound Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-to-sound-generation-on-vgg-sound","task":"Video-to-Sound Generation","dataset":"VGG-Sound","model":"MMAudio-S-16kHz","rank_in_archive_order":1,"of":8,"metrics":{"FAD":"0.79","FD":"5.22"},"uses_additional_data":false},{"leaderboard":"/sota/video-to-sound-generation-on-vgg-sound","task":"Video-to-Sound Generation","dataset":"VGG-Sound","model":"MMAudio-L-44.1kHz","rank_in_archive_order":3,"of":8,"metrics":{"FAD":"0.97","FD":"4.72"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2412.15322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15322"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hkchengrex/MMAudio","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"09143760aafd552c","entry":"attention","repo":"hkchengrex/MMAudio","repo_kind":"official","path":"mmaudio/model/transformer_layers.py","file_url":"https://github.com/hkchengrex/MMAudio/blob/HEAD/mmaudio/model/transformer_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09143760aafd552c"}},{"code_sha256_prefix":"97b05d5fed34027b","entry":"dynamic_range_compression_torch","repo":"hkchengrex/MMAudio","repo_kind":"official","path":"mmaudio/ext/mel_converter.py","file_url":"https://github.com/hkchengrex/MMAudio/blob/HEAD/mmaudio/ext/mel_converter.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97b05d5fed34027b"}},{"code_sha256_prefix":"5dbb4533aa8c2b8f","entry":"modulate","repo":"hkchengrex/MMAudio","repo_kind":"official","path":"mmaudio/model/transformer_layers.py","file_url":"https://github.com/hkchengrex/MMAudio/blob/HEAD/mmaudio/model/transformer_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5dbb4533aa8c2b8f"}},{"code_sha256_prefix":"d589f15a67884195","entry":"spectral_normalize_torch","repo":"hkchengrex/MMAudio","repo_kind":"official","path":"mmaudio/ext/mel_converter.py","file_url":"https://github.com/hkchengrex/MMAudio/blob/HEAD/mmaudio/ext/mel_converter.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d589f15a67884195"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}