{"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/audio-visual-synchronization","name":"Audio-Visual Synchronization","slug":"audio-visual-synchronization","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":32,"papers_with_code":11,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/acappella","name":"Acappella","full_name":"","num_papers_in_archive":5},{"url":"/dataset/vggsound-sparse","name":"VGGSound-Sparse","full_name":"","num_papers_in_archive":5},{"url":"/dataset/avsync15","name":"AVSync15","full_name":"","num_papers_in_archive":2},{"url":"/dataset/avs-benchmark","name":"AVS Benchmark","full_name":"Audio-Visual Synchrony Benchmark","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":32,"of":32,"of_with_code":11,"tagged_in_all":32,"counts":{"archive_papers_tagged":32,"with_a_code_link":11,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":32,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"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/synchformer-efficient-synchronization-from","slug":"synchformer-efficient-synchronization-from","title":"Synchformer: Efficient Synchronization from Sparse Cues","date":"2024-01-29","arxiv_id":"2401.16423","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/synchformer-efficient-synchronization-from#ran","syntology_url":"https://syntology.ai/paper/2401.16423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16423"}},"official":{"repos":["v-iashin/synchformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/multimodal-transformer-distillation-for-audio","slug":"multimodal-transformer-distillation-for-audio","title":"Multimodal Transformer Distillation for Audio-Visual Synchronization","date":"2022-10-27","arxiv_id":"2210.15563","repositories_listed":2,"syntology":null},{"url":"/paper/sparse-in-space-and-time-audio-visual","slug":"sparse-in-space-and-time-audio-visual","title":"Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors","date":"2022-10-13","arxiv_id":"2210.07055","repositories_listed":2,"syntology":null},{"url":"/paper/cogenav-versatile-audio-visual-representation","slug":"cogenav-versatile-audio-visual-representation","title":"CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization","date":"2025-05-06","arxiv_id":"2505.03186","repositories_listed":1,"syntology":null},{"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/musetalk-real-time-high-quality-lip","slug":"musetalk-real-time-high-quality-lip","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","date":"2024-10-14","arxiv_id":"2410.10122","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"7 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/musetalk-real-time-high-quality-lip#ran","syntology_url":"https://syntology.ai/paper/2410.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10122"}},"official":{"repos":["tmelyralab/musetalk"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explicit-correlation-learning-for","slug":"explicit-correlation-learning-for","title":"Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection","date":"2024-04-30","arxiv_id":"2404.19171","repositories_listed":1,"syntology":null},{"url":"/paper/peavs-perceptual-evaluation-of-audio-visual","slug":"peavs-perceptual-evaluation-of-audio-visual","title":"PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores","date":"2024-04-10","arxiv_id":"2404.07336","repositories_listed":1,"syntology":null},{"url":"/paper/target-active-speaker-detection-with-audio","slug":"target-active-speaker-detection-with-audio","title":"Target Active Speaker Detection with Audio-visual Cues","date":"2023-05-22","arxiv_id":"2305.12831","repositories_listed":1,"syntology":null},{"url":"/paper/vocalist-an-audio-visual-synchronisation","slug":"vocalist-an-audio-visual-synchronisation","title":"VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices","date":"2022-04-05","arxiv_id":"2204.02090","repositories_listed":1,"syntology":null},{"url":"/paper/neural-pitch-shifting-and-time-stretching","slug":"neural-pitch-shifting-and-time-stretching","title":"Neural Pitch-Shifting and Time-Stretching with Controllable LPCNet","date":"2021-10-05","arxiv_id":"2110.02360","repositories_listed":1,"syntology":null},{"url":null,"slug":"kling-foley-multimodal-diffusion-transformer","title":"Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation","date":"2025-06-24","arxiv_id":"2506.19774","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-sync-video-generation-with-multi-stream","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","date":"2025-06-09","arxiv_id":"2506.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"omniresponse-online-multimodal-conversational","title":"OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions","date":"2025-05-27","arxiv_id":"2505.21724","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepaudio-v1-towards-multi-modal-multi-stage","title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation","date":"2025-03-28","arxiv_id":"2503.22265","repositories_listed":0,"syntology":null},{"url":null,"slug":"unisync-a-unified-framework-for-audio-visual","title":"UniSync: A Unified Framework for Audio-Visual Synchronization","date":"2025-03-20","arxiv_id":"2503.16357","repositories_listed":0,"syntology":null},{"url":null,"slug":"freak-frequency-modulated-high-fidelity-and","title":"FREAK: Frequency-modulated High-fidelity and Real-time Audio-driven Talking Portrait Synthesis","date":"2025-03-06","arxiv_id":"2503.04067","repositories_listed":0,"syntology":null},{"url":null,"slug":"draw-an-audio-leveraging-multi-instruction","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","date":"2024-09-10","arxiv_id":"2409.06135","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-review-and-taxonomy-of-audio","title":"A Comprehensive Review and Taxonomy of Audio-Visual Synchronization Techniques for Realistic Speech Animation","date":"2024-07-24","arxiv_id":"2407.17430","repositories_listed":0,"syntology":null},{"url":null,"slug":"realtalk-real-time-and-realistic-audio-driven","title":"RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network","date":"2024-06-26","arxiv_id":"2406.18284","repositories_listed":0,"syntology":null},{"url":null,"slug":"coavt-a-cognition-inspired-unified-audio","title":"CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing","date":"2024-01-22","arxiv_id":"2401.12264","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-analysis-of-deep-fake-algorithms","title":"Comparative Analysis of Deep-Fake Algorithms","date":"2023-09-06","arxiv_id":"2309.03295","repositories_listed":0,"syntology":null},{"url":null,"slug":"plug-the-leaks-advancing-audio-driven-talking","title":"Audio-driven Talking Face Generation with Stabilized Synchronization Loss","date":"2023-07-18","arxiv_id":"2307.09368","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-audio-visual-synchronization-for-lip","title":"On the Audio-visual Synchronization for Lip-to-Speech Synthesis","date":"2023-03-01","arxiv_id":"2303.00502","repositories_listed":0,"syntology":null},{"url":null,"slug":"synctalkface-talking-face-generation-with","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","date":"2022-11-02","arxiv_id":"2211.00924","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-audio-visual-synchronization-for","title":"Rethinking Audio-visual Synchronization for Active Speaker Detection","date":"2022-06-21","arxiv_id":"2206.10421","repositories_listed":0,"syntology":null},{"url":null,"slug":"looking-into-your-speech-learning-cross-modal","title":"Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation","date":"2021-03-25","arxiv_id":"2104.02775","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-listen-and-attend-co-attention-network","title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","date":"2020-08-13","arxiv_id":"2008.05789","repositories_listed":0,"syntology":null},{"url":null,"slug":"identity-preserving-realistic-talking-face","title":"Identity-Preserving Realistic Talking Face Generation","date":"2020-05-25","arxiv_id":"2005.12318","repositories_listed":0,"syntology":null},{"url":null,"slug":"realistic-speech-driven-facial-animation-with","title":"Realistic Speech-Driven Facial Animation with GANs","date":"2019-06-14","arxiv_id":"1906.06337","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-attention-modules-for-audio-visual","title":"On Attention Modules for Audio-Visual Synchronization","date":"2018-12-14","arxiv_id":"1812.06071","repositories_listed":0,"syntology":null},{"url":null,"slug":"facedirector-continuous-control-of-facial","title":"FaceDirector: Continuous Control of Facial Performance in Video","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":3,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/audio-visual-synchronization/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/audio-visual-synchronization/papers/ran/1","json":"/task/audio-visual-synchronization/papers/ran/1.json","rows":3}],"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":"4ebacc5f5d669f813292bf67c3a93883448e938a7809e973817b041caa76acb1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}