{"url":"/task/video-to-sound-generation","name":"Video-to-Sound Generation","slug":"video-to-sound-generation","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"},{"name":"Music","url":"/area/music"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":9,"papers_with_code":6,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-to-sound-generation-on-vgg-sound","slug":"video-to-sound-generation-on-vgg-sound","dataset":"VGG-Sound","dataset_url":"/dataset/vgg-sound","rows_in_archive":8,"metrics":["FAD","FD","KLD"],"first_row_in_archive_order":{"model":"MMAudio-S-16kHz","paper_title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","paper_url":"/paper/taming-multimodal-joint-training-for-high","paper_date":"2024-12-19","arxiv_id":"2412.15322","code_links":[{"title":"hkchengrex/MMAudio","url":"https://github.com/hkchengrex/MMAudio"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/vgg-sound","name":"VGG-Sound","full_name":"","num_papers_in_archive":211}],"subtasks":[],"parent_tasks":[{"url":"/task/audio-generation","name":"Audio Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":6,"of":6,"tagged_in_all":9,"items":[{"url":"/paper/taming-multimodal-joint-training-for-high","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","date":"2024-12-19","arxiv_id":"2412.15322","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/tell-what-you-hear-from-what-you-see-video-to","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","date":"2024-11-08","arxiv_id":"2411.05679","repositories_listed":1,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":6}},{"url":"/paper/temporally-aligned-audio-for-video-with","title":"Temporally Aligned Audio for Video with Autoregression","date":"2024-09-20","arxiv_id":"2409.13689","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/read-watch-and-scream-sound-generation-from","title":"Read, Watch and Scream! Sound Generation from Text and Video","date":"2024-07-08","arxiv_id":"2407.05551","repositories_listed":1,"syntology":{"n":22,"n_ran":18,"n_unverified":4,"n_pointer_only":22}},{"url":"/paper/frieren-efficient-video-to-audio-generation","title":"Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching","date":"2024-06-01","arxiv_id":"2406.00320","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/v2a-mapper-a-lightweight-solution-for-vision","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","date":"2023-08-18","arxiv_id":"2308.09300","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}