{"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/lip-reading","name":"Lip Reading","slug":"lip-reading","description_markdown":"**Lip Reading** is a task to infer the speech content in a video by using only the visual information, especially the lip movements. It has many crucial applications in practice, such as assisting audio-based speech recognition, biometric authentication and aiding hearing-impaired people.\n\n\n<span class=\"description-source\">Source: [Mutual Information Maximization for Effective Lip Reading ](https://arxiv.org/abs/2003.06439)</span>","categories":[{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":153,"papers_with_code":49,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":6,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/lip-reading-on-grid-corpus-mixed-speech","slug":"lip-reading-on-grid-corpus-mixed-speech","dataset":"GRID corpus (mixed-speech)","dataset_url":"/dataset/grid","rows_in_archive":1,"metrics":["WER"],"first_row_in_archive_order":{"model":"Lip2Wav","paper_title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","paper_url":"/paper/learning-individual-speaking-styles-for","paper_date":"2020-05-17","arxiv_id":"2005.08209","code_links":[{"title":"Rudrabha/Lip2Wav","url":"https://github.com/Rudrabha/Lip2Wav"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-individual-speaking-styles-for#ran","syntology_url":"https://syntology.ai/paper/2005.08209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08209"}},"official":{"repos":["Rudrabha/Lip2Wav"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/lip-reading-on-lrw","slug":"lip-reading-on-lrw","dataset":"LRW","dataset_url":"/dataset/lrw","rows_in_archive":1,"metrics":["WER"],"first_row_in_archive_order":{"model":"Lip2Wav","paper_title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","paper_url":"/paper/learning-individual-speaking-styles-for","paper_date":"2020-05-17","arxiv_id":"2005.08209","code_links":[{"title":"Rudrabha/Lip2Wav","url":"https://github.com/Rudrabha/Lip2Wav"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-individual-speaking-styles-for#ran","syntology_url":"https://syntology.ai/paper/2005.08209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08209"}},"official":{"repos":["Rudrabha/Lip2Wav"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/lip-reading-on-tcd-timit-corpus-mixed-speech","slug":"lip-reading-on-tcd-timit-corpus-mixed-speech","dataset":"TCD-TIMIT corpus (mixed-speech)","dataset_url":"/dataset/timit","rows_in_archive":1,"metrics":["WER"],"first_row_in_archive_order":{"model":"Lip2Wav","paper_title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","paper_url":"/paper/learning-individual-speaking-styles-for","paper_date":"2020-05-17","arxiv_id":"2005.08209","code_links":[{"title":"Rudrabha/Lip2Wav","url":"https://github.com/Rudrabha/Lip2Wav"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-individual-speaking-styles-for#ran","syntology_url":"https://syntology.ai/paper/2005.08209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08209"}},"official":{"repos":["Rudrabha/Lip2Wav"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/lrw","name":"LRW","full_name":"Lip Reading in the Wild","num_papers_in_archive":188},{"url":"/dataset/timit","name":"TIMIT","full_name":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","num_papers_in_archive":31},{"url":"/dataset/grid","name":"GRID Dataset","full_name":"","num_papers_in_archive":10},{"url":"/dataset/lrw-1000","name":"CAS-VSR-W1k (LRW-1000)","full_name":"CAS-VSR-W1k (LRW-1000)","num_papers_in_archive":9},{"url":"/dataset/glips","name":"GLips","full_name":"German Lips","num_papers_in_archive":6},{"url":"/dataset/cas-vsr-s101","name":"CAS-VSR-S101","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/lip-password-classification","name":"Lip password classification"}],"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":2,"rows_per_page":100,"shown":100,"of":153,"of_with_code":49,"tagged_in_all":153,"counts":{"archive_papers_tagged":153,"with_a_code_link":49,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":153,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":14,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":14,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/combining-residual-networks-with-lstms-for","slug":"combining-residual-networks-with-lstms-for","title":"Combining Residual Networks with LSTMs for Lipreading","date":"2017-03-12","arxiv_id":"1703.04105","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/combining-residual-networks-with-lstms-for#ran","syntology_url":"https://syntology.ai/paper/1703.04105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04105"}},"official":{"repos":["tstafylakis/Lipreading-ResNet"],"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":["listed","unlocated"]}}},{"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/mixspeech-cross-modality-self-learning-with","slug":"mixspeech-cross-modality-self-learning-with","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","date":"2023-03-09","arxiv_id":"2303.05309","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/mixspeech-cross-modality-self-learning-with#ran","syntology_url":"https://syntology.ai/paper/2303.05309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05309"}},"official":{"repos":["exgc/avmust-ted"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-audio-visual-speech-representation-1","slug":"learning-audio-visual-speech-representation-1","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","date":"2022-01-05","arxiv_id":"2201.02184","repositories_listed":2,"syntology":null},{"url":"/paper/authnet-a-deep-learning-based-authentication","slug":"authnet-a-deep-learning-based-authentication","title":"AuthNet: A Deep Learning based Authentication Mechanism using Temporal Facial Feature Movements","date":"2020-12-04","arxiv_id":"2012.02515","repositories_listed":2,"syntology":null},{"url":"/paper/lipreading-using-temporal-convolutional","slug":"lipreading-using-temporal-convolutional","title":"Lipreading using Temporal Convolutional Networks","date":"2020-01-23","arxiv_id":"2001.08702","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/lipreading-using-temporal-convolutional#ran","syntology_url":"https://syntology.ai/paper/2001.08702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08702"}},"official":null}},{"url":"/paper/lrw-1000-a-naturally-distributed-large-scale","slug":"lrw-1000-a-naturally-distributed-large-scale","title":"LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild","date":"2018-10-16","arxiv_id":"1810.06990","repositories_listed":2,"syntology":null},{"url":"/paper/transforming-faces-into-video-stories","slug":"transforming-faces-into-video-stories","title":"Transforming faces into video stories -- VideoFace2.0","date":"2025-05-04","arxiv_id":"2505.02060","repositories_listed":1,"syntology":null},{"url":"/paper/lend-a-hand-semi-training-free-cued-speech","slug":"lend-a-hand-semi-training-free-cued-speech","title":"Lend a Hand: Semi Training-Free Cued Speech Recognition via MLLM-Driven Hand Modeling for Barrier-free Communication","date":"2025-03-11","arxiv_id":"2503.21785","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-lip-reading-adapting-to-your","slug":"personalized-lip-reading-adapting-to-your","title":"Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language","date":"2024-09-02","arxiv_id":"2409.00986","repositories_listed":1,"syntology":null},{"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/mtga-multi-view-temporal-granularity-aligned","slug":"mtga-multi-view-temporal-granularity-aligned","title":"MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading","date":"2024-04-18","arxiv_id":"2404.11979","repositories_listed":1,"syntology":null},{"url":"/paper/where-visual-speech-meets-language-vsp-llm","slug":"where-visual-speech-meets-language-vsp-llm","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","date":"2024-02-23","arxiv_id":"2402.15151","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":2,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"10 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/where-visual-speech-meets-language-vsp-llm#ran","syntology_url":"https://syntology.ai/paper/2402.15151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15151"}},"official":{"repos":["sally-sh/vsp-llm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-text-to-articulate-talk-deep-text-to","slug":"neural-text-to-articulate-talk-deep-text-to","title":"Neural Text to Articulate Talk: Deep Text to Audiovisual Speech Synthesis achieving both Auditory and Photo-realism","date":"2023-12-11","arxiv_id":"2312.06613","repositories_listed":1,"syntology":null},{"url":"/paper/do-vsr-models-generalize-beyond-lrs3","slug":"do-vsr-models-generalize-beyond-lrs3","title":"Do VSR Models Generalize Beyond LRS3?","date":"2023-11-23","arxiv_id":"2311.14063","repositories_listed":1,"syntology":null},{"url":"/paper/learning-separable-hidden-unit-contributions","slug":"learning-separable-hidden-unit-contributions","title":"Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading","date":"2023-10-08","arxiv_id":"2310.05058","repositories_listed":1,"syntology":null},{"url":"/paper/selftalk-a-self-supervised-commutative","slug":"selftalk-a-self-supervised-commutative","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","date":"2023-06-19","arxiv_id":"2306.10799","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selftalk-a-self-supervised-commutative#ran","syntology_url":"https://syntology.ai/paper/2306.10799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.10799"}},"official":{"repos":["psyai-net/SelfTalk_release"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"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/a-novel-interpretable-and-generalizable-re","slug":"a-novel-interpretable-and-generalizable-re","title":"A Novel Interpretable and Generalizable Re-synchronization Model for Cued Speech based on a Multi-Cuer Corpus","date":"2023-06-05","arxiv_id":"2306.02596","repositories_listed":1,"syntology":null},{"url":"/paper/lipvoicer-generating-speech-from-silent","slug":"lipvoicer-generating-speech-from-silent","title":"LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading","date":"2023-06-05","arxiv_id":"2306.03258","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/lipvoicer-generating-speech-from-silent#ran","syntology_url":"https://syntology.ai/paper/2306.03258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03258"}},"official":{"repos":["yochaiye/LipVoicer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/seeing-what-you-said-talking-face-generation","slug":"seeing-what-you-said-talking-face-generation","title":"Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert","date":"2023-03-29","arxiv_id":"2303.17480","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"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 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) · 0 unverified","sample_list":"/paper/seeing-what-you-said-talking-face-generation#ran","syntology_url":"https://syntology.ai/paper/2303.17480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17480"}},"official":{"repos":["sxjdwang/talklip"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/geneface-generalized-and-high-fidelity-audio","slug":"geneface-generalized-and-high-fidelity-audio","title":"GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis","date":"2023-01-31","arxiv_id":"2301.13430","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/geneface-generalized-and-high-fidelity-audio#ran","syntology_url":"https://syntology.ai/paper/2301.13430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13430"}},"official":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/audio-visual-efficient-conformer-for-robust","slug":"audio-visual-efficient-conformer-for-robust","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","date":"2023-01-04","arxiv_id":"2301.01456","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/audio-visual-efficient-conformer-for-robust#ran","syntology_url":"https://syntology.ai/paper/2301.01456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.01456"}},"official":{"repos":["burchim/avec"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lip-sync-matters-a-novel-multimodal-forgery","slug":"lip-sync-matters-a-novel-multimodal-forgery","title":"Lip Sync Matters: A Novel Multimodal Forgery Detector","date":"2022-11-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/relaxed-attention-for-transformer-models","slug":"relaxed-attention-for-transformer-models","title":"Relaxed Attention for Transformer Models","date":"2022-09-20","arxiv_id":"2209.09735","repositories_listed":1,"syntology":null},{"url":"/paper/training-strategies-for-improved-lip-reading","slug":"training-strategies-for-improved-lip-reading","title":"Training Strategies for Improved Lip-reading","date":"2022-09-03","arxiv_id":"2209.01383","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-adaptive-lip-reading-with-user","slug":"speaker-adaptive-lip-reading-with-user","title":"Speaker-adaptive Lip Reading with User-dependent Padding","date":"2022-08-09","arxiv_id":"2208.04498","repositories_listed":1,"syntology":null},{"url":"/paper/distinguishing-homophenes-using-multi-head-1","slug":"distinguishing-homophenes-using-multi-head-1","title":"Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading","date":"2022-04-04","arxiv_id":"2204.01725","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modality-associative-bridging-through-1","slug":"multi-modality-associative-bridging-through-1","title":"Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video","date":"2022-04-04","arxiv_id":"2204.01265","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/multi-modality-associative-bridging-through-1#ran","syntology_url":"https://syntology.ai/paper/2204.01265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01265"}},"official":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/visual-keyword-spotting-with-attention","slug":"visual-keyword-spotting-with-attention","title":"Visual Keyword Spotting with Attention","date":"2021-10-29","arxiv_id":"2110.15957","repositories_listed":1,"syntology":null},{"url":"/paper/selective-hearing-through-lip-reading","slug":"selective-hearing-through-lip-reading","title":"Selective Listening by Synchronizing Speech with Lips","date":"2021-06-14","arxiv_id":"2106.07150","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-of-global-and-local-1","slug":"contrastive-learning-of-global-and-local-1","title":"Contrastive Learning of Global-Local Video Representations","date":"2021-04-07","arxiv_id":"2104.05418","repositories_listed":1,"syntology":null},{"url":"/paper/learn-an-effective-lip-reading-model-without","slug":"learn-an-effective-lip-reading-model-without","title":"Learn an Effective Lip Reading Model without Pains","date":"2020-11-15","arxiv_id":"2011.07557","repositories_listed":1,"syntology":null},{"url":"/paper/lip-reading-with-densely-connected-temporal","slug":"lip-reading-with-densely-connected-temporal","title":"Lip-reading with Densely Connected Temporal Convolutional Networks","date":"2020-09-29","arxiv_id":"2009.14233","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-wake-words-audio-visual-keyword","slug":"seeing-wake-words-audio-visual-keyword","title":"Seeing wake words: Audio-visual Keyword Spotting","date":"2020-09-02","arxiv_id":"2009.01225","repositories_listed":1,"syntology":null},{"url":"/paper/learning-individual-speaking-styles-for","slug":"learning-individual-speaking-styles-for","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","date":"2020-05-17","arxiv_id":"2005.08209","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-individual-speaking-styles-for#ran","syntology_url":"https://syntology.ai/paper/2005.08209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08209"}},"official":{"repos":["Rudrabha/Lip2Wav"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/synchronous-bidirectional-learning-for","slug":"synchronous-bidirectional-learning-for","title":"Synchronous Bidirectional Learning for Multilingual Lip Reading","date":"2020-05-08","arxiv_id":"2005.03846","repositories_listed":1,"syntology":null},{"url":"/paper/mutual-information-maximization-for-effective","slug":"mutual-information-maximization-for-effective","title":"Mutual Information Maximization for Effective Lip Reading","date":"2020-03-13","arxiv_id":"2003.06439","repositories_listed":1,"syntology":null},{"url":"/paper/deformation-flow-based-two-stream-network-for","slug":"deformation-flow-based-two-stream-network-for","title":"Deformation Flow Based Two-Stream Network for Lip Reading","date":"2020-03-12","arxiv_id":"2003.05709","repositories_listed":1,"syntology":null},{"url":"/paper/can-we-read-speech-beyond-the-lips-rethinking","slug":"can-we-read-speech-beyond-the-lips-rethinking","title":"Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition","date":"2020-03-06","arxiv_id":"2003.03206","repositories_listed":1,"syntology":null},{"url":"/paper/hearing-lips-improving-lip-reading-by","slug":"hearing-lips-improving-lip-reading-by","title":"Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers","date":"2019-11-26","arxiv_id":"1911.11502","repositories_listed":1,"syntology":null},{"url":"/paper/talking-face-generation-by-adversarially","slug":"talking-face-generation-by-adversarially","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","date":"2018-07-20","arxiv_id":"1807.07860","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/talking-face-generation-by-adversarially#ran","syntology_url":"https://syntology.ai/paper/1807.07860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.07860"}},"official":null}},{"url":"/paper/end-to-end-speech-driven-facial-animation","slug":"end-to-end-speech-driven-facial-animation","title":"End-to-End Speech-Driven Facial Animation with Temporal GANs","date":"2018-05-23","arxiv_id":"1805.09313","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-speech-driven-facial-animation#ran","syntology_url":"https://syntology.ai/paper/1805.09313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09313"}},"official":null}},{"url":"/paper/lip2audspec-speech-reconstruction-from-silent","slug":"lip2audspec-speech-reconstruction-from-silent","title":"Lip2AudSpec: Speech reconstruction from silent lip movements video","date":"2017-10-26","arxiv_id":"1710.09798","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/lip2audspec-speech-reconstruction-from-silent#ran","syntology_url":"https://syntology.ai/paper/1710.09798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.09798"}},"official":{"repos":["hassanhub/LipReading"],"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/xflow-1d-2d-cross-modal-deep-neural-networks","slug":"xflow-1d-2d-cross-modal-deep-neural-networks","title":"XFlow: Cross-modal Deep Neural Networks for Audiovisual Classification","date":"2017-09-02","arxiv_id":"1709.00572","repositories_listed":1,"syntology":null},{"url":"/paper/estimating-speech-from-lip-dynamics","slug":"estimating-speech-from-lip-dynamics","title":"Estimating speech from lip dynamics","date":"2017-08-03","arxiv_id":"1708.01198","repositories_listed":1,"syntology":null},{"url":null,"slug":"visualspeaker-visually-guided-3d-avatar-lip","title":"VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis","date":"2025-07-08","arxiv_id":"2507.06060","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":"development-and-evaluation-of-a-deep-learning-1","title":"Development and evaluation of a deep learning algorithm for German word recognition from lip movements","date":"2025-04-22","arxiv_id":"2504.15792","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":"vallr-visual-asr-language-model-for-lip","title":"VALLR: Visual ASR Language Model for Lip Reading","date":"2025-03-27","arxiv_id":"2503.21408","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-persian-lip-reading-in-surena-v","title":"Integrating Persian Lip Reading in Surena-V Humanoid Robot for Human-Robot Interaction","date":"2025-01-23","arxiv_id":"2501.13996","repositories_listed":0,"syntology":null},{"url":null,"slug":"glam-sign-greek-language-multimodal-lip","title":"GLaM-Sign: Greek Language Multimodal Lip Reading with Integrated Sign Language Accessibility","date":"2025-01-09","arxiv_id":"2501.05213","repositories_listed":0,"syntology":null},{"url":null,"slug":"lipgen-viseme-guided-lip-video-generation-for","title":"LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition","date":"2025-01-08","arxiv_id":"2501.04204","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-transformers-for-action-unit","title":"Spatio-temporal Transformers for Action Unit Classification with Event Cameras","date":"2024-10-29","arxiv_id":"2410.21958","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":"neuromorphic-facial-analysis-with-cross-modal","title":"Neuromorphic Facial Analysis with Cross-Modal Supervision","date":"2024-09-16","arxiv_id":"2409.10213","repositories_listed":0,"syntology":null},{"url":null,"slug":"ral-redundancy-aware-lipreading-model-based","title":"RAL:Redundancy-Aware Lipreading Model Based on Differential Learning with Symmetric Views","date":"2024-09-09","arxiv_id":"2409.05307","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-speech-driven-3d-facial-animation","title":"Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert","date":"2024-07-01","arxiv_id":"2407.01034","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-multi-modal-speech-in-painting-a","title":"Robust Multi-Modal Speech In-Painting: A Sequence-to-Sequence Approach","date":"2024-06-02","arxiv_id":"2406.00901","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-to-non-barrier-communication-gloss","title":"Bridge to Non-Barrier Communication: Gloss-Prompted Fine-grained Cued Speech Gesture Generation with Diffusion Model","date":"2024-04-30","arxiv_id":"2404.19277","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-lip-reading-with-multi-scale-video","title":"Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder","date":"2024-04-08","arxiv_id":"2404.05466","repositories_listed":0,"syntology":null},{"url":null,"slug":"landmark-guided-cross-speaker-lip-reading","title":"Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization","date":"2024-03-24","arxiv_id":"2403.16071","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-attention-fusion-of-visual-and","title":"Cross-Attention Fusion of Visual and Geometric Features for Large Vocabulary Arabic Lipreading","date":"2024-02-18","arxiv_id":"2402.11520","repositories_listed":0,"syntology":null},{"url":null,"slug":"computation-and-parameter-efficient-multi","title":"Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition","date":"2024-01-31","arxiv_id":"2401.17604","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-lip-segmentation-techniques-in","title":"Exploring Lip Segmentation Techniques in Computer Vision: A Comparative Analysis","date":"2023-11-20","arxiv_id":"2311.11992","repositories_listed":0,"syntology":null},{"url":null,"slug":"dualtalker-a-cross-modal-dual-learning","title":"DualTalker: A Cross-Modal Dual Learning Approach for Speech-Driven 3D Facial Animation","date":"2023-11-08","arxiv_id":"2311.04766","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-lip-reading-in-romanian-with-cross","title":"End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition","date":"2023-10-07","arxiv_id":"2310.04858","repositories_listed":0,"syntology":null},{"url":null,"slug":"lip-reading-for-low-resource-languages-by","title":"Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge","date":"2023-08-18","arxiv_id":"2308.09311","repositories_listed":0,"syntology":null},{"url":"/paper/lip2vec-efficient-and-robust-visual-speech","slug":"lip2vec-efficient-and-robust-visual-speech","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping","date":"2023-08-11","arxiv_id":"2308.06112","repositories_listed":0,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":2,"n_honours":4,"n_violates":1,"n_no_contract":11,"n_pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 4 honoured, 1 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lip2vec-efficient-and-robust-visual-speech#ran","syntology_url":"https://syntology.ai/paper/2308.06112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06112"}},"official":null}},{"url":null,"slug":"leveraging-visemes-for-better-visual-speech","title":"Leveraging Visemes for Better Visual Speech Representation and Lip Reading","date":"2023-07-19","arxiv_id":"2307.10157","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotional-speech-driven-animation-with","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","date":"2023-06-15","arxiv_id":"2306.08990","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-spatio-temporal-facial","title":"Deep Learning-based Spatio Temporal Facial Feature Visual Speech Recognition","date":"2023-04-30","arxiv_id":"2305.00552","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixelrnn-in-pixel-recurrent-neural-networks","title":"PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors","date":"2023-04-11","arxiv_id":"2304.05440","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-level-persian-lipreading-dataset","title":"Word-level Persian Lipreading Dataset","date":"2023-04-08","arxiv_id":"2304.04068","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthvsr-scaling-up-visual-speech-recognition","title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","date":"2023-03-30","arxiv_id":"2303.17200","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-scale-multimodal-dataset-of-human","title":"A large-scale multimodal dataset of human speech recognition","date":"2023-03-15","arxiv_id":"2303.08295","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":"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":"speech-driven-video-editing-via-an-audio","title":"Speech Driven Video Editing via an Audio-Conditioned Diffusion Model","date":"2023-01-10","arxiv_id":"2301.04474","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-video-face-hallucination-with","title":"Audio-visual video face hallucination with frequency supervision and cross modality support by speech based lip reading loss","date":"2022-11-20","arxiv_id":"2211.10883","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":"audio-visual-speech-enhancement-and","title":"Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings","date":"2022-10-31","arxiv_id":"2210.17456","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-frame-structure-for-cloud-based-audio","title":"A Novel Frame Structure for Cloud-Based Audio-Visual Speech Enhancement in Multimodal Hearing-aids","date":"2022-10-24","arxiv_id":"2210.13127","repositories_listed":0,"syntology":null},{"url":null,"slug":"clean-text-and-full-body-transformer","title":"Clean Text and Full-Body Transformer: Microsoft's Submission to the WMT22 Shared Task on Sign Language Translation","date":"2022-10-24","arxiv_id":"2210.13326","repositories_listed":0,"syntology":null},{"url":null,"slug":"vcse-time-domain-visual-contextual-speaker","title":"VCSE: Time-Domain Visual-Contextual Speaker Extraction Network","date":"2022-10-09","arxiv_id":"2210.06177","repositories_listed":0,"syntology":null},{"url":"/paper/visual-speech-recognition-in-a-driver","slug":"visual-speech-recognition-in-a-driver","title":"Visual Speech Recognition in a Driver Assistance System","date":"2022-08-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-moocs-for-lip-reading-using-synthetic","title":"Towards MOOCs for Lipreading: Using Synthetic Talking Heads to Train Humans in Lipreading at Scale","date":"2022-08-21","arxiv_id":"2208.09796","repositories_listed":0,"syntology":null},{"url":null,"slug":"lip-listening-mixing-senses-to-understand","title":"Lip-Listening: Mixing Senses to Understand Lips using Cross Modality Knowledge Distillation for Word-Based Models","date":"2022-06-05","arxiv_id":"2207.05692","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-speaker-specific-lip-to-speech","title":"Learning Speaker-specific Lip-to-Speech Generation","date":"2022-06-04","arxiv_id":"2206.02050","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":"expression-preserving-face-frontalization","title":"Expression-preserving face frontalization improves visually assisted speech processing","date":"2022-04-06","arxiv_id":"2204.02810","repositories_listed":0,"syntology":null},{"url":"/paper/a-multimodal-german-dataset-for-automatic-lip","slug":"a-multimodal-german-dataset-for-automatic-lip","title":"A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning","date":"2022-02-27","arxiv_id":"2202.13403","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-grained-spatio-temporal-features","title":"Multi-Grained Spatio-Temporal Features Perceived Network for Event-Based Lip-Reading","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lipsound2-self-supervised-pre-training-for","title":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","date":"2021-12-09","arxiv_id":"2112.04748","repositories_listed":0,"syntology":null},{"url":"/paper/audio-visual-synchronisation-in-the-wild","slug":"audio-visual-synchronisation-in-the-wild","title":"Audio-Visual Synchronisation in the wild","date":"2021-12-08","arxiv_id":"2112.04432","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-of-global-and-local-2","title":"Contrastive Learning of Global and Local Video Representations","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":17,"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":17,"papers_where_code_ran_first_page":"/task/lip-reading/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":"archive","page":2,"of":2,"url":"/task/lip-reading/papers/2","json":"/task/lip-reading/papers/2.json","rows":53},{"order":"ran","page":1,"of":1,"url":"/task/lip-reading/papers/ran/1","json":"/task/lip-reading/papers/ran/1.json","rows":17}],"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":"012a0f07f22ad93c178d7901768bf0f9804fbfe314a1bb957a643d8ceee83bb8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}