{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/taming-multimodal-joint-training-for-high#ran","syntology_url":"https://syntology.ai/paper/2412.15322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15322"}},"official":{"repos":["hkchengrex/MMAudio"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":9,"of":9,"of_with_code":6,"tagged_in_all":9,"counts":{"archive_papers_tagged":9,"with_a_code_link":6,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/taming-multimodal-joint-training-for-high","slug":"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":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/taming-multimodal-joint-training-for-high#ran","syntology_url":"https://syntology.ai/paper/2412.15322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15322"}},"official":{"repos":["hkchengrex/MMAudio"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tell-what-you-hear-from-what-you-see-video-to","slug":"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":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tell-what-you-hear-from-what-you-see-video-to#ran","syntology_url":"https://syntology.ai/paper/2411.05679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05679"}},"official":{"repos":["DragonLiu1995/multimodal-llm-for-audio-gen"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/temporally-aligned-audio-for-video-with","slug":"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_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/temporally-aligned-audio-for-video-with#ran","syntology_url":"https://syntology.ai/paper/2409.13689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13689"}},"official":{"repos":["ilpoviertola/V-AURA"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/read-watch-and-scream-sound-generation-from","slug":"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_constructed":0,"n_ran_checked":3,"n_instrument":15,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":22,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 15 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/read-watch-and-scream-sound-generation-from#ran","syntology_url":"https://syntology.ai/paper/2407.05551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05551"}},"official":{"repos":["naver-ai/rewas"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/frieren-efficient-video-to-audio-generation","slug":"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":15,"n_constructed":0,"n_ran_checked":7,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":4,"n_no_contract":2,"n_pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 4 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/frieren-efficient-video-to-audio-generation#ran","syntology_url":"https://syntology.ai/paper/2406.00320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00320"}},"official":{"repos":["cyanbx/Frieren-V2A"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/v2a-mapper-a-lightweight-solution-for-vision","slug":"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},{"url":null,"slug":"video-foley-two-stage-video-to-sound","title":"Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound","date":"2024-08-21","arxiv_id":"2408.11915","repositories_listed":0,"syntology":null},{"url":"/paper/masked-generative-video-to-audio-transformers","slug":"masked-generative-video-to-audio-transformers","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","date":"2024-07-15","arxiv_id":"2407.10387","repositories_listed":0,"syntology":null},{"url":null,"slug":"varietysound-timbre-controllable-video-to","title":"VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglement","date":"2022-11-19","arxiv_id":"2211.10666","repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/video-to-sound-generation-on-vgg-sound","since_archive":"/sota/video-to-sound-generation-on-vgg-sound#since-judged","papers_judged":4,"placed":0}]},"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/task/video-to-sound-generation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/video-to-sound-generation/papers/ran/1","json":"/task/video-to-sound-generation/papers/ran/1.json","rows":5}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"e023dd99b57faff8661a33e3f94d4ef324ac3c7713c307ea52139ef0d394b89b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}