{"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":"/dataset/lrw","name":"LRW","full_name":"Lip Reading in the Wild","description_markdown":"The **Lip Reading in the Wild** (**LRW**) dataset  a large-scale audio-visual database that contains 500 different words from over 1,000 speakers. Each utterance has 29 frames, whose boundary is centered around the target word. The database is divided into training, validation and test sets. The training set contains at least 800 utterances for each class while the validation and test sets contain 50 utterances.\r\n\r\nSource: [Towards Pose-invariant Lip-Reading](https://arxiv.org/abs/1911.06095)\r\nImage Source: [https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrw1.html](https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrw1.html)","description_withheld":null,"homepage":"https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrw1.html","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Lip Reading in the Wild","first_author":null,"url":"https://doi.org/10.1007/978-3-319-54184-6_6"},"license":{"name":"Custom (research-only, non-commercial, attribution)","url":"https://www.bbc.co.uk/rd/projects/lip-reading-datasets"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Lipreading","url":"/task/lipreading","datasets_with_task":"/datasets/task/lipreading"},{"name":"Lip to Speech Synthesis","url":"/task/lip-to-speech-synthesis","datasets_with_task":"/datasets/task/lip-to-speech-synthesis"},{"name":"Audio-Visual Speech Recognition","url":"/task/audio-visual-speech-recognition","datasets_with_task":"/datasets/task/audio-visual-speech-recognition"},{"name":"Lip Reading","url":"/task/lip-reading","datasets_with_task":"/datasets/task/lip-reading"},{"name":"Unconstrained Lip-synchronization","url":"/task/lip-sync","datasets_with_task":"/datasets/task/lip-sync"},{"name":"Visual Keyword Spotting","url":"/task/visual-keyword-spotting","datasets_with_task":"/datasets/task/visual-keyword-spotting"},{"name":"Talking Face Generation","url":"/task/talking-face-generation","datasets_with_task":"/datasets/task/talking-face-generation"},{"name":"Landmark-based Lipreading","url":"/task/landmark-based-lipreading","datasets_with_task":"/datasets/task/landmark-based-lipreading"}],"languages":[],"variants":["LRW","Lip Reading in the Wild","Lipreading in the Wild"],"data_loaders":[{"repo":"https://github.com/Rudrabha/Wav2Lip","url":"https://arxiv.org/abs/2008.10010","frameworks":["pytorch"]}],"num_papers_in_archive":188,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/lipreading-on-lip-reading-in-the-wild","task":"Lipreading","dataset_variant":"Lip Reading in the Wild","rows":22,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"SyncVSR (Word Boundary)","paper":"/paper/syncvsr-data-efficient-visual-speech","metrics":{"Top-1 Accuracy":"95.0"},"code_links":[{"title":"KAIST-AILab/SyncVSR","url":"https://github.com/KAIST-AILab/SyncVSR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/landmark-based-lipreading-on-lrw","task":"Landmark-based Lipreading","dataset_variant":"LRW","rows":5,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"SyncVSR (Word Boundary)","paper":"/paper/syncvsr-data-efficient-visual-speech","metrics":{"Top 1 Accuracy":"80.3"},"code_links":[{"title":"KAIST-AILab/SyncVSR","url":"https://github.com/KAIST-AILab/SyncVSR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrw","task":"Audio-Visual Speech Recognition","dataset_variant":"LRW","rows":3,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"AVCRFormer","paper":"/paper/audio-visual-speech-recognition-based-on","metrics":{"Top-1 Accuracy":"98.81"},"code_links":[{"title":"SMIL-SPCRAS/AVCRFormer","url":"https://github.com/SMIL-SPCRAS/AVCRFormer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/lip-sync-on-lrw","task":"Unconstrained Lip-synchronization","dataset_variant":"LRW","rows":2,"metrics":["FID","LSE-C","LSE-D"],"first_row_in_archive_order":{"model":"Wav2Lip + GAN","paper":"/paper/a-lip-sync-expert-is-all-you-need-for-speech","metrics":{"FID":"2.475","LSE-C":"7.263","LSE-D":"6.774"},"code_links":[{"title":"Rudrabha/Wav2Lip","url":"https://github.com/Rudrabha/Wav2Lip"},{"title":"mowshon/lipsync","url":"https://github.com/mowshon/lipsync"},{"title":"PrashanthaTP/wav2mov","url":"https://github.com/PrashanthaTP/wav2mov"},{"title":"rockstar-0000/lip_sync_test","url":"https://github.com/rockstar-0000/lip_sync_test"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/lip-reading-on-lrw","task":"Lip Reading","dataset_variant":"LRW","rows":1,"metrics":["WER"],"first_row_in_archive_order":{"model":"Lip2Wav","paper":"/paper/learning-individual-speaking-styles-for","metrics":{"WER":"34.2"},"code_links":[{"title":"Rudrabha/Lip2Wav","url":"https://github.com/Rudrabha/Lip2Wav"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/lip-to-speech-synthesis-on-lrw","task":"Lip to Speech Synthesis","dataset_variant":"LRW","rows":1,"metrics":["ESTOI","PESQ","STOI"],"first_row_in_archive_order":{"model":"Lip2Wav","paper":"/paper/learning-individual-speaking-styles-for","metrics":{"ESTOI":"0.344","PESQ":"1.197","STOI":"0.543"},"code_links":[{"title":"Rudrabha/Lip2Wav","url":"https://github.com/Rudrabha/Lip2Wav"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/talking-face-generation-on-lrw","task":"Talking Face Generation","dataset_variant":"LRW","rows":1,"metrics":["LMD","SSIM"],"first_row_in_archive_order":{"model":"LipGAN","paper":"/paper/towards-automatic-face-to-face-translation-1","metrics":{"LMD":"0.60","SSIM":"0.96"},"code_links":[{"title":"Rudrabha/LipGAN","url":"https://github.com/Rudrabha/LipGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-keyword-spotting-on-lrw","task":"Visual Keyword Spotting","dataset_variant":"LRW","rows":1,"metrics":["Top-1 Accuracy","Top-5 Accuracy","mAP"],"first_row_in_archive_order":{"model":"Transpotter","paper":"/paper/visual-keyword-spotting-with-attention","metrics":{"Top-1 Accuracy":"85.8","Top-5 Accuracy":"99.6","mAP":"64.1"},"code_links":[{"title":"prajwalkr/transpotter","url":"https://github.com/prajwalkr/transpotter"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":29,"of":29,"counts":{"papers_with_a_benchmark_row":29,"with_a_code_link":20,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":29,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":4,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/syncvsr-data-efficient-visual-speech","slug":"syncvsr-data-efficient-visual-speech","title":"SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization","date":"2024-06-18","arxiv_id":"2406.12233","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/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,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/another-point-of-view-on-visual-speech","slug":"another-point-of-view-on-visual-speech","title":"Another Point of View on Visual Speech Recognition","date":"2023-08-20","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/accurate-and-resource-efficient-lipreading","slug":"accurate-and-resource-efficient-lipreading","title":"Accurate and Resource-Efficient Lipreading with Efficientnetv2 and Transformers","date":"2022-05-23","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-semantic-spatio-temporal-graph","slug":"adaptive-semantic-spatio-temporal-graph","title":"Adaptive Semantic-Spatio-Temporal Graph Convolutional Network for Lip Reading","date":"2021-08-16","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-lip-sync-expert-is-all-you-need-for-speech","slug":"a-lip-sync-expert-is-all-you-need-for-speech","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","date":"2020-08-23","arxiv_id":"2008.10010","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["Rudrabha/Wav2Lip"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-lip-sync-expert-is-all-you-need-for-speech#ran","syntology_url":"https://syntology.ai/paper/2008.10010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10010"}}}},{"paper":"/paper/towards-practical-lipreading-with-distilled","slug":"towards-practical-lipreading-with-distilled","title":"Towards Practical Lipreading with Distilled and Efficient Models","date":"2020-07-13","arxiv_id":"2007.06504","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spotfast-networks-with-memory-augmented","slug":"spotfast-networks-with-memory-augmented","title":"SpotFast Networks with Memory Augmented Lateral Transformers for Lipreading","date":"2020-05-21","arxiv_id":"2005.10903","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/discriminative-multi-modality-speech","slug":"discriminative-multi-modality-speech","title":"Discriminative Multi-modality Speech Recognition","date":"2020-05-12","arxiv_id":"2005.05592","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pseudo-convolutional-policy-gradient-for","slug":"pseudo-convolutional-policy-gradient-for","title":"Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading","date":"2020-03-09","arxiv_id":"2003.03983","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-automatic-face-to-face-translation-1","slug":"towards-automatic-face-to-face-translation-1","title":"Towards Automatic Face-to-Face Translation","date":"2020-03-01","arxiv_id":"2003.00418","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Rudrabha/LipGAN"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-automatic-face-to-face-translation-1#ran","syntology_url":"https://syntology.ai/paper/2003.00418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00418"}}}},{"paper":"/paper/lipreading-using-temporal-convolutional","slug":"lipreading-using-temporal-convolutional","title":"Lipreading using Temporal Convolutional Networks","date":"2020-01-23","arxiv_id":"2001.08702","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/multi-grained-spatio-temporal-modeling-for","slug":"multi-grained-spatio-temporal-modeling-for","title":"Multi-Grained Spatio-temporal Modeling for Lip-reading","date":"2019-08-30","arxiv_id":"1908.11618","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-audiovisual-speech-recognition","slug":"end-to-end-audiovisual-speech-recognition","title":"End-to-end Audiovisual Speech Recognition","date":"2018-02-18","arxiv_id":"1802.06424","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/syncvsr-data-efficient-visual-speech","slug":"syncvsr-data-efficient-visual-speech","title":"SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization","date":"2024-06-18","arxiv_id":"2406.12233","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/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,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/another-point-of-view-on-visual-speech","slug":"another-point-of-view-on-visual-speech","title":"Another Point of View on Visual Speech Recognition","date":"2023-08-20","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/accurate-and-resource-efficient-lipreading","slug":"accurate-and-resource-efficient-lipreading","title":"Accurate and Resource-Efficient Lipreading with Efficientnetv2 and Transformers","date":"2022-05-23","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-semantic-spatio-temporal-graph","slug":"adaptive-semantic-spatio-temporal-graph","title":"Adaptive Semantic-Spatio-Temporal Graph Convolutional Network for Lip Reading","date":"2021-08-16","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-lip-sync-expert-is-all-you-need-for-speech","slug":"a-lip-sync-expert-is-all-you-need-for-speech","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","date":"2020-08-23","arxiv_id":"2008.10010","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["Rudrabha/Wav2Lip"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-lip-sync-expert-is-all-you-need-for-speech#ran","syntology_url":"https://syntology.ai/paper/2008.10010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10010"}}}},{"paper":"/paper/towards-practical-lipreading-with-distilled","slug":"towards-practical-lipreading-with-distilled","title":"Towards Practical Lipreading with Distilled and Efficient Models","date":"2020-07-13","arxiv_id":"2007.06504","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spotfast-networks-with-memory-augmented","slug":"spotfast-networks-with-memory-augmented","title":"SpotFast Networks with Memory Augmented Lateral Transformers for Lipreading","date":"2020-05-21","arxiv_id":"2005.10903","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/discriminative-multi-modality-speech","slug":"discriminative-multi-modality-speech","title":"Discriminative Multi-modality Speech Recognition","date":"2020-05-12","arxiv_id":"2005.05592","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pseudo-convolutional-policy-gradient-for","slug":"pseudo-convolutional-policy-gradient-for","title":"Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading","date":"2020-03-09","arxiv_id":"2003.03983","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-automatic-face-to-face-translation-1","slug":"towards-automatic-face-to-face-translation-1","title":"Towards Automatic Face-to-Face Translation","date":"2020-03-01","arxiv_id":"2003.00418","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Rudrabha/LipGAN"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-automatic-face-to-face-translation-1#ran","syntology_url":"https://syntology.ai/paper/2003.00418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00418"}}}},{"paper":"/paper/lipreading-using-temporal-convolutional","slug":"lipreading-using-temporal-convolutional","title":"Lipreading using Temporal Convolutional Networks","date":"2020-01-23","arxiv_id":"2001.08702","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/multi-grained-spatio-temporal-modeling-for","slug":"multi-grained-spatio-temporal-modeling-for","title":"Multi-Grained Spatio-temporal Modeling for Lip-reading","date":"2019-08-30","arxiv_id":"1908.11618","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-audiovisual-speech-recognition","slug":"end-to-end-audiovisual-speech-recognition","title":"End-to-end Audiovisual Speech Recognition","date":"2018-02-18","arxiv_id":"1802.06424","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/dataset/lrw/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/lrw/papers/ran/1","json":"/dataset/lrw/papers/ran/1.json","rows":7}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":7,"samples_harvested":24,"samples_ran":21,"samples_constructed":1,"samples_ran_checked":15,"samples_ran_instrument_failed":6,"samples_unverified":3,"pointer_only_for_licence":7,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":7,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"1c800bfbf6ff7b8093635dd1611b421c3a72719320057cae2f025caac7becbc3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}