{"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-speech-recognition/papers/ran/1","list_of":"/task/audio-visual-speech-recognition","task":"Audio-Visual Speech Recognition","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,14],"of":14,"counts":{"archive_papers_tagged":100,"with_a_code_link":42,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":100,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":12,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":12,"listed_every_run_a_failure_of_syntologys_instrument":2,"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"},"first_page":"/task/audio-visual-speech-recognition/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/multi-task-corrupted-prediction-for-learning","slug":"multi-task-corrupted-prediction-for-learning","title":"Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation","date":"2025-01-23","arxiv_id":"2504.18539","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-corrupted-prediction-for-learning#ran","syntology_url":"https://syntology.ai/paper/2504.18539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.18539"}},"official":{"repos":["sungnyun/cav2vec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-are-strong-audio-visual","slug":"large-language-models-are-strong-audio-visual","title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners","date":"2024-09-18","arxiv_id":"2409.12319","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":2,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/large-language-models-are-strong-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2409.12319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12319"}},"official":{"repos":["umbertocappellazzo/llama-avsr"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-video-temporal-dynamics-with-cross","slug":"learning-video-temporal-dynamics-with-cross","title":"Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition","date":"2024-07-04","arxiv_id":"2407.03563","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":2,"n_ran_checked":8,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-video-temporal-dynamics-with-cross#ran","syntology_url":"https://syntology.ai/paper/2407.03563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03563"}},"official":{"repos":["sungnyun/avsr-temporal-dynamics"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/whisper-flamingo-integrating-visual-features","slug":"whisper-flamingo-integrating-visual-features","title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","date":"2024-06-14","arxiv_id":"2406.10082","repositories_listed":1,"syntology":{"n":18,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":18,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/whisper-flamingo-integrating-visual-features#ran","syntology_url":"https://syntology.ai/paper/2406.10082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10082"}},"official":{"repos":["roudimit/whisper-flamingo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/it-s-never-too-late-fusing-acoustic","slug":"it-s-never-too-late-fusing-acoustic","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","date":"2024-02-08","arxiv_id":"2402.05457","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/it-s-never-too-late-fusing-acoustic#ran","syntology_url":"https://syntology.ai/paper/2402.05457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05457"}},"official":null}},{"url":"/paper/multichannel-av-wav2vec2-a-framework-for","slug":"multichannel-av-wav2vec2-a-framework-for","title":"Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation","date":"2024-01-07","arxiv_id":"2401.03468","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":2,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multichannel-av-wav2vec2-a-framework-for#ran","syntology_url":"https://syntology.ai/paper/2401.03468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03468"}},"official":{"repos":["zqs01/multi-channel-wav2vec2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hearing-lips-in-noise-universal-viseme","slug":"hearing-lips-in-noise-universal-viseme","title":"Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition","date":"2023-06-18","arxiv_id":"2306.10563","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hearing-lips-in-noise-universal-viseme#ran","syntology_url":"https://syntology.ai/paper/2306.10563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.10563"}},"official":{"repos":["yuchen005/univpm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mir-gan-refining-frame-level-modality","slug":"mir-gan-refining-frame-level-modality","title":"MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition","date":"2023-06-18","arxiv_id":"2306.10567","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/mir-gan-refining-frame-level-modality#ran","syntology_url":"https://syntology.ai/paper/2306.10567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.10567"}},"official":{"repos":["yuchen005/mir-gan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/auto-avsr-audio-visual-speech-recognition","slug":"auto-avsr-audio-visual-speech-recognition","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","date":"2023-03-25","arxiv_id":"2303.14307","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/auto-avsr-audio-visual-speech-recognition#ran","syntology_url":"https://syntology.ai/paper/2303.14307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14307"}},"official":{"repos":["mpc001/auto_avsr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/watch-or-listen-robust-audio-visual-speech","slug":"watch-or-listen-robust-audio-visual-speech","title":"Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring","date":"2023-03-15","arxiv_id":"2303.08536","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/watch-or-listen-robust-audio-visual-speech#ran","syntology_url":"https://syntology.ai/paper/2303.08536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08536"}},"official":{"repos":["ms-dot-k/AVSR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/olkavs-an-open-large-scale-korean-audio","slug":"olkavs-an-open-large-scale-korean-audio","title":"OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset","date":"2023-01-16","arxiv_id":"2301.06375","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/olkavs-an-open-large-scale-korean-audio#ran","syntology_url":"https://syntology.ai/paper/2301.06375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.06375"}},"official":{"repos":["iip-sogang/olkavs-avspeech"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-uni-modal-self-supervised-learning-1","slug":"leveraging-uni-modal-self-supervised-learning-1","title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition","date":"2022-02-24","arxiv_id":"2203.07996","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/leveraging-uni-modal-self-supervised-learning-1#ran","syntology_url":"https://syntology.ai/paper/2203.07996","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07996"}},"official":{"repos":["lumia-group/leveraging-self-supervised-learning-for-avsr"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ci-avsr-a-cantonese-audio-visual-speech","slug":"ci-avsr-a-cantonese-audio-visual-speech","title":"CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition","date":"2022-01-11","arxiv_id":"2201.03804","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ci-avsr-a-cantonese-audio-visual-speech#ran","syntology_url":"https://syntology.ai/paper/2201.03804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03804"}},"official":{"repos":["hltchkust/ci-avsr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-self-supervised-audio-visual-speech","slug":"robust-self-supervised-audio-visual-speech","title":"Robust Self-Supervised Audio-Visual Speech Recognition","date":"2022-01-05","arxiv_id":"2201.01763","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-self-supervised-audio-visual-speech#ran","syntology_url":"https://syntology.ai/paper/2201.01763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.01763"}},"official":{"repos":["facebookresearch/av_hubert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}}],"record_sha256":"fa848f06d83ec3159544197f32d6a95a43bd098e904e91624e1d260fbc2598e0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}