{"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","name":"Audio-Visual Speech Recognition","slug":"audio-visual-speech-recognition","description_markdown":"Audio-visual speech recognition is the task of transcribing a paired audio and visual stream into text.","categories":[{"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":100,"papers_with_code":42,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":7,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrs3-ted","slug":"audio-visual-speech-recognition-on-lrs3-ted","dataset":"LRS3-TED","dataset_url":"/dataset/lrs3-ted","rows_in_archive":12,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"MMS-LLaMA","paper_title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","paper_url":"/paper/mms-llama-efficient-llm-based-audio-visual-1","paper_date":"2025-03-14","arxiv_id":"2503.11315","code_links":[{"title":"JeongHun0716/MMS-LLaMA","url":"https://github.com/JeongHun0716/MMS-LLaMA"}],"syntology":null}},{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrs2","slug":"audio-visual-speech-recognition-on-lrs2","dataset":"LRS2","dataset_url":"/dataset/lrs2","rows_in_archive":8,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"Whisper-Flamingo","paper_title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","paper_url":"/paper/whisper-flamingo-integrating-visual-features","paper_date":"2024-06-14","arxiv_id":"2406.10082","code_links":[{"title":"roudimit/whisper-flamingo","url":"https://github.com/roudimit/whisper-flamingo"}],"syntology":{"n":18,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":7,"n_honours":5,"n_violates":1,"n_no_contract":2,"n_pointer_only":18,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 3 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":8,"n_unverified":7,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrw","slug":"audio-visual-speech-recognition-on-lrw","dataset":"LRW","dataset_url":"/dataset/lrw","rows_in_archive":3,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"AVCRFormer","paper_title":"Audio-Visual Speech Recognition based on Regulated Transformer and Spatio-Temporal Fusion Strategy for Driver Assistive Systems","paper_url":"/paper/audio-visual-speech-recognition-based-on","paper_date":"2024-05-09","arxiv_id":null,"code_links":[{"title":"SMIL-SPCRAS/AVCRFormer","url":"https://github.com/SMIL-SPCRAS/AVCRFormer"}],"syntology":null}},{"leaderboard":"/sota/audio-visual-speech-recognition-on-cas-vsr","slug":"audio-visual-speech-recognition-on-cas-vsr","dataset":"CAS-VSR-S101","dataset_url":"/dataset/cas-vsr-s101","rows_in_archive":1,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"ES³ Base*","paper_title":"ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations","paper_url":"/paper/es3-evolving-self-supervised-learning-of","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/lrw","name":"LRW","full_name":"Lip Reading in the Wild","num_papers_in_archive":188},{"url":"/dataset/lrs2","name":"LRS2","full_name":"Lip Reading Sentences 2","num_papers_in_archive":115},{"url":"/dataset/how2","name":"How2","full_name":"","num_papers_in_archive":84},{"url":"/dataset/lrs3-ted","name":"LRS3-TED","full_name":"","num_papers_in_archive":63},{"url":"/dataset/lrw-1000","name":"CAS-VSR-W1k (LRW-1000)","full_name":"CAS-VSR-W1k (LRW-1000)","num_papers_in_archive":9},{"url":"/dataset/misp2021","name":"MISP2021","full_name":"Multimodal Information Based Speech Processing 2021","num_papers_in_archive":3},{"url":"/dataset/cas-vsr-s101","name":"CAS-VSR-S101","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/text-to-speech","name":"Text to Speech"}],"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":100,"of":100,"of_with_code":42,"tagged_in_all":100,"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"},"items":[{"url":"/paper/deep-audio-visual-speech-recognition","slug":"deep-audio-visual-speech-recognition","title":"Deep Audio-Visual Speech Recognition","date":"2018-09-06","arxiv_id":"1809.02108","repositories_listed":4,"syntology":null},{"url":"/paper/end-to-end-audio-visual-speech-recognition","slug":"end-to-end-audio-visual-speech-recognition","title":"End-to-end Audio-visual Speech Recognition with Conformers","date":"2021-02-12","arxiv_id":"2102.06657","repositories_listed":3,"syntology":null},{"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/discriminative-multi-modality-speech","slug":"discriminative-multi-modality-speech","title":"Discriminative Multi-modality Speech Recognition","date":"2020-05-12","arxiv_id":"2005.05592","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/mms-llama-efficient-llm-based-audio-visual-1","slug":"mms-llama-efficient-llm-based-audio-visual-1","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","date":"2025-03-14","arxiv_id":"2503.11315","repositories_listed":1,"syntology":null},{"url":"/paper/zero-avsr-zero-shot-audio-visual-speech","slug":"zero-avsr-zero-shot-audio-visual-speech","title":"Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations","date":"2025-03-08","arxiv_id":"2503.06273","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-representation-learning-via","slug":"audio-visual-representation-learning-via","title":"Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models","date":"2025-02-09","arxiv_id":"2502.05766","repositories_listed":1,"syntology":null},{"url":"/paper/mwhisper-flamingo-for-multilingual-audio","slug":"mwhisper-flamingo-for-multilingual-audio","title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition","date":"2025-02-03","arxiv_id":"2502.01547","repositories_listed":1,"syntology":null},{"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/listening-and-seeing-again-generative-error","slug":"listening-and-seeing-again-generative-error","title":"Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition","date":"2025-01-03","arxiv_id":"2501.04038","repositories_listed":1,"syntology":null},{"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":5,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"9 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; 4 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":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-00624","slug":"2408-00624","title":"SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data","date":"2024-08-01","arxiv_id":"2408.00624","repositories_listed":1,"syntology":null},{"url":"/paper/tailored-design-of-audio-visual-speech","slug":"tailored-design-of-audio-visual-speech","title":"Tailored Design of Audio-Visual Speech Recognition Models using Branchformers","date":"2024-07-09","arxiv_id":"2407.06606","repositories_listed":1,"syntology":null},{"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":7,"n_instrument":5,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 5 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":7,"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":8,"n_instrument":3,"n_unverified":7,"n_honours":5,"n_violates":1,"n_no_contract":2,"n_pointer_only":18,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 3 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":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/audio-visual-speech-recognition-based-on","slug":"audio-visual-speech-recognition-based-on","title":"Audio-Visual Speech Recognition based on Regulated Transformer and Spatio-Temporal Fusion Strategy for Driver Assistive Systems","date":"2024-05-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-dropout-induced-modality-bias-on","slug":"a-study-of-dropout-induced-modality-bias-on","title":"A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition","date":"2024-03-07","arxiv_id":"2403.04245","repositories_listed":1,"syntology":null},{"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":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 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/rtfs-net-recurrent-time-frequency-modelling","slug":"rtfs-net-recurrent-time-frequency-modelling","title":"RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation","date":"2023-09-29","arxiv_id":"2309.17189","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/rtfs-net-recurrent-time-frequency-modelling#ran","syntology_url":"https://syntology.ai/paper/2309.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17189"}},"official":{"repos":["spkgyk/RTFS-Net"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/improving-audio-visual-speech-recognition-by","slug":"improving-audio-visual-speech-recognition-by","title":"Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder","date":"2023-08-14","arxiv_id":"2308.08488","repositories_listed":1,"syntology":null},{"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/opensr-open-modality-speech-recognition-via","slug":"opensr-open-modality-speech-recognition-via","title":"OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment","date":"2023-06-10","arxiv_id":"2306.06410","repositories_listed":1,"syntology":null},{"url":"/paper/mavd-the-first-open-large-scale-mandarin","slug":"mavd-the-first-open-large-scale-mandarin","title":"MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information","date":"2023-06-04","arxiv_id":"2306.02263","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-the-hidden-talent-of-web-scale","slug":"prompting-the-hidden-talent-of-web-scale","title":"Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization","date":"2023-05-18","arxiv_id":"2305.11095","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-global-interaction-and-local","slug":"cross-modal-global-interaction-and-local","title":"Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition","date":"2023-05-16","arxiv_id":"2305.09212","repositories_listed":1,"syntology":null},{"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/muavic-a-multilingual-audio-visual-corpus-for","slug":"muavic-a-multilingual-audio-visual-corpus-for","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","date":"2023-03-01","arxiv_id":"2303.00628","repositories_listed":1,"syntology":null},{"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/jointly-learning-visual-and-auditory-speech","slug":"jointly-learning-visual-and-auditory-speech","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","date":"2022-12-12","arxiv_id":"2212.06246","repositories_listed":1,"syntology":null},{"url":"/paper/visual-context-driven-audio-feature","slug":"visual-context-driven-audio-feature","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","date":"2022-07-13","arxiv_id":"2207.06020","repositories_listed":1,"syntology":null},{"url":"/paper/ci-avsr-a-cantonese-audio-visual-speech-1","slug":"ci-avsr-a-cantonese-audio-visual-speech-1","title":"CI-AVSR: A Cantonese Audio-Visual Speech Datasetfor In-car Command Recognition","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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"]}}},{"url":"/paper/av-taris-online-audio-visual-speech","slug":"av-taris-online-audio-visual-speech","title":"AV Taris: Online Audio-Visual Speech Recognition","date":"2020-12-14","arxiv_id":"2012.07467","repositories_listed":1,"syntology":null},{"url":"/paper/should-we-hard-code-the-recurrence-concept-or","slug":"should-we-hard-code-the-recurrence-concept-or","title":"Should we hard-code the recurrence concept or learn it instead ? Exploring the Transformer architecture for Audio-Visual Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09297","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-teach-dnns-to-pay-attention-to-the","slug":"how-to-teach-dnns-to-pay-attention-to-the","title":"How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition","date":"2020-04-17","arxiv_id":"2004.08250","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-neural-network-transducer-for-audio","slug":"recurrent-neural-network-transducer-for-audio","title":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition","date":"2019-11-08","arxiv_id":"1911.04890","repositories_listed":1,"syntology":null},{"url":"/paper/lrs3-ted-a-large-scale-dataset-for-visual","slug":"lrs3-ted-a-large-scale-dataset-for-visual","title":"LRS3-TED: a large-scale dataset for visual speech recognition","date":"2018-09-03","arxiv_id":"1809.00496","repositories_listed":1,"syntology":null},{"url":null,"slug":"vicocktail-automated-multi-modal-data","title":"ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition","date":"2025-06-05","arxiv_id":"2506.04635","repositories_listed":0,"syntology":null},{"url":null,"slug":"cocktail-party-audio-visual-speech","title":"Cocktail-Party Audio-Visual Speech Recognition","date":"2025-06-02","arxiv_id":"2506.02178","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-and-enhancing-llm-based-avsr-a-sparse","title":"Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach","date":"2025-05-20","arxiv_id":"2505.14336","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-multimodal-information-based-speech-2","title":"The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition","date":"2025-05-20","arxiv_id":"2505.13971","repositories_listed":0,"syntology":null},{"url":null,"slug":"swinlip-an-efficient-visual-speech-encoder","title":"SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer","date":"2025-05-07","arxiv_id":"2505.04394","repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-lips-a-chinese-audio-visual-speech","title":"Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides","date":"2025-04-21","arxiv_id":"2504.15066","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-aware-speech-recognition-for-noisy","title":"Visual-Aware Speech Recognition for Noisy Scenarios","date":"2025-04-09","arxiv_id":"2504.07229","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-audio-visual-speech-recognition-via","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","date":"2025-03-09","arxiv_id":"2503.06362","repositories_listed":0,"syntology":null},{"url":null,"slug":"mohave-mixture-of-hierarchical-audio-visual","title":"MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition","date":"2025-02-11","arxiv_id":"2502.10447","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapter-based-multi-agent-avsr-extension-for","title":"Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models","date":"2025-02-03","arxiv_id":"2502.01709","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncovering-the-visual-contribution-in-audio","title":"Uncovering the Visual Contribution in Audio-Visual Speech Recognition","date":"2024-12-22","arxiv_id":"2412.17129","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantitative-analysis-of-audio-visual-tasks","title":"Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective","date":"2024-09-29","arxiv_id":"2409.19575","repositories_listed":0,"syntology":null},{"url":null,"slug":"dcim-avsr-efficient-audio-visual-speech","title":"DCIM-AVSR : Efficient Audio-Visual Speech Recognition via Dual Conformer Interaction Module","date":"2024-08-31","arxiv_id":"2409.00481","repositories_listed":0,"syntology":null},{"url":null,"slug":"msrs-training-multimodal-speech-recognition","title":"MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization","date":"2024-06-25","arxiv_id":"2406.17614","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn2talk-3d-talking-face-learns-from-2d","title":"Learn2Talk: 3D Talking Face Learns from 2D Talking Face","date":"2024-04-19","arxiv_id":"2404.12888","repositories_listed":0,"syntology":null},{"url":null,"slug":"xlavs-r-cross-lingual-audio-visual-speech","title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception","date":"2024-03-21","arxiv_id":"2403.14402","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-audio-visual-speech-recognition","title":"Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer","date":"2024-03-14","arxiv_id":"2405.12983","repositories_listed":0,"syntology":null},{"url":null,"slug":"slideavsr-a-dataset-of-paper-explanation","title":"SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition","date":"2024-01-18","arxiv_id":"2401.09759","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlca-avsr-multi-layer-cross-attention-fusion","title":"MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition","date":"2024-01-07","arxiv_id":"2401.03424","repositories_listed":0,"syntology":null},{"url":"/paper/es3-evolving-self-supervised-learning-of","slug":"es3-evolving-self-supervised-learning-of","title":"ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"av-cpl-continuous-pseudo-labeling-for-audio","title":"AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition","date":"2023-09-29","arxiv_id":"2309.17395","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-multimodal-information-based-speech-1","title":"The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction","date":"2023-09-15","arxiv_id":"2309.08348","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-npu-aslp-system-for-audio-visual-speech","title":"The NPU-ASLP System for Audio-Visual Speech Recognition in MISP 2022 Challenge","date":"2023-03-11","arxiv_id":"2303.06341","repositories_listed":0,"syntology":null},{"url":"/paper/audio-visual-speech-and-gesture-recognition","slug":"audio-visual-speech-and-gesture-recognition","title":"Audio-Visual Speech and Gesture Recognition by Sensors of Mobile Devices","date":"2023-02-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"av-data2vec-self-supervised-learning-of-audio","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","date":"2023-02-10","arxiv_id":"2302.06419","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-purpose-audio-visual-corpus-for-multi","title":"A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset","date":"2023-01-21","arxiv_id":"2301.10180","repositories_listed":0,"syntology":null},{"url":null,"slug":"revise-self-supervised-speech-resynthesis-1","title":"ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/revise-self-supervised-speech-resynthesis","slug":"revise-self-supervised-speech-resynthesis","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","date":"2022-12-21","arxiv_id":"2212.11377","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-modality-specific-representations","title":"Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning","date":"2022-12-10","arxiv_id":"2212.05301","repositories_listed":0,"syntology":null},{"url":null,"slug":"vatlm-visual-audio-text-pre-training-with","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","date":"2022-11-21","arxiv_id":"2211.11275","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-audio-visual-speech-recognition","title":"Streaming Audio-Visual Speech Recognition with Alignment Regularization","date":"2022-11-03","arxiv_id":"2211.02133","repositories_listed":0,"syntology":null},{"url":null,"slug":"kaggle-competition-cantonese-audio-visual","title":"Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands","date":"2022-07-06","arxiv_id":"2207.02663","repositories_listed":0,"syntology":null},{"url":null,"slug":"rusavic-corpus-russian-audio-visual-speech-in","title":"RUSAVIC Corpus: Russian Audio-Visual Speech in Cars","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-contextually-fused-audio-visual","title":"Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition","date":"2022-02-15","arxiv_id":"2202.07428","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-video-front-ends-for-audio","title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video","date":"2022-01-25","arxiv_id":"2201.10439","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-progress-in-the-cuhk-dysarthric-speech","title":"Recent Progress in the CUHK Dysarthric Speech Recognition System","date":"2022-01-15","arxiv_id":"2201.05845","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-uni-modal-self-supervised-learning","title":"Leveraging Uni-Modal Self-Supervised Learning for Multimodal Audio-visual Speech Recognition","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-speech-recognition-is-worth-32","title":"Audio-Visual Speech Recognition is Worth 32$\\times$32$\\times$8 Voxels","date":"2021-09-20","arxiv_id":"2109.09536","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-vocabulary-audio-visual-speech","title":"Large-vocabulary Audio-visual Speech Recognition in Noisy Environments","date":"2021-09-10","arxiv_id":"2109.04894","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-attention-mechanism-and","title":"Spatio-Temporal Attention Mechanism and Knowledge Distillation for Lip Reading","date":"2021-08-07","arxiv_id":"2108.03543","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusing-information-streams-in-end-to-end","title":"Fusing information streams in end-to-end audio-visual speech recognition","date":"2021-04-19","arxiv_id":"2104.09482","repositories_listed":0,"syntology":null},{"url":"/paper/part-based-lipreading-for-audio-visual-speech","slug":"part-based-lipreading-for-audio-visual-speech","title":"Part-based Lipreading for Audio-Visual Speech Recognition","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/lip-graph-assisted-audio-visual-speech","slug":"lip-graph-assisted-audio-visual-speech","title":"Lip Graph Assisted Audio-Visual Speech Recognition Using Bidirectional Synchronous Fusion","date":"2020-10-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/audio-visual-recognition-of-overlapped-speech","slug":"audio-visual-recognition-of-overlapped-speech","title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset","date":"2020-01-06","arxiv_id":"2001.01656","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-adversarial-attacks-on-audio-visual","title":"Detecting Adversarial Attacks On Audiovisual Speech Recognition","date":"2019-12-18","arxiv_id":"1912.08639","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-lombard-effect-influence-on","title":"Investigating the Lombard Effect Influence on End-to-End Audio-Visual Speech Recognition","date":"2019-06-05","arxiv_id":"1906.02112","repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-attention-for-end-to-end-audio","title":"Modality Attention for End-to-End Audio-visual Speech Recognition","date":"2018-11-13","arxiv_id":"1811.05250","repositories_listed":0,"syntology":null},{"url":"/paper/audio-visual-speech-recognition-with-a-hybrid","slug":"audio-visual-speech-recognition-with-a-hybrid","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","date":"2018-09-28","arxiv_id":"1810.00108","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-lipreading-sentences-with-active","title":"Towards Lipreading Sentences with Active Appearance Models","date":"2018-05-29","arxiv_id":"1805.11688","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-machine-learning-integrating","title":"Multimodal Machine Learning: Integrating Language, Vision and Speech","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multimodal-representation-learning-from","title":"Deep Multimodal Representation Learning from Temporal Data","date":"2017-04-11","arxiv_id":"1704.03152","repositories_listed":0,"syntology":null},{"url":null,"slug":"auxiliary-multimodal-lstm-for-audio-visual","title":"Auxiliary Multimodal LSTM for Audio-visual Speech Recognition and Lipreading","date":"2017-01-16","arxiv_id":"1701.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-speech-recognition-using-deep","title":"Audio Visual Speech Recognition using Deep Recurrent Neural Networks","date":"2016-11-09","arxiv_id":"1611.02879","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multimodal-learning-for-audio-visual","title":"Deep Multimodal Learning for Audio-Visual Speech Recognition","date":"2015-01-22","arxiv_id":"1501.05396","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-speech-recognition","title":"Visual Speech Recognition","date":"2014-09-03","arxiv_id":"1409.1411","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognition-of-isolated-words-using-zernike","title":"Recognition of Isolated Words using Zernike and MFCC features for Audio Visual Speech Recognition","date":"2014-07-04","arxiv_id":"1407.1165","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-a-synchronous-corpus-of-acoustic-and","title":"Building a synchronous corpus of acoustic and 3D facial marker data for adaptive audio-visual speech synthesis","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sutav-a-turkish-audio-visual-database","title":"SUTAV: A Turkish Audio-Visual Database","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":15,"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":14,"papers_where_code_ran_first_page":"/task/audio-visual-speech-recognition/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-speech-recognition/papers/ran/1","json":"/task/audio-visual-speech-recognition/papers/ran/1.json","rows":14}],"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":"537425a53336972e45737d9b0806a02f2f952cc591a07fc2b7d4a5edab4bf88f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}