{"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/lrs3-ted","name":"LRS3-TED","full_name":null,"description_markdown":"LRS3-TED is a multi-modal dataset for visual and audio-visual speech recognition. It includes face tracks from over 400 hours of TED and TEDx videos, along with the corresponding subtitles and word alignment boundaries. The new dataset is substantially larger in scale compared to other public datasets that are available for general research. \r\n\r\nSource: [LRS3-TED: a large-scale dataset for visual speech recognition](https://arxiv.org/pdf/1809.00496v2.pdf)","description_withheld":null,"homepage":"https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrs3.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/lrs3-ted-a-large-scale-dataset-for-visual","title":"LRS3-TED: a large-scale dataset for visual speech recognition","first_author":"Triantafyllos Afouras","url":null},"license":{"name":"Creative Commons BY-NC-ND 4.0 license","url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"},{"name":"Active Speaker Detection","url":"/task/active-speaker-detection","datasets_with_task":"/datasets/task/active-speaker-detection"},{"name":"Visual Speech Recognition","url":"/task/visual-speech-recognition","datasets_with_task":"/datasets/task/visual-speech-recognition"},{"name":"Lipreading","url":"/task/lipreading","datasets_with_task":"/datasets/task/lipreading"},{"name":"Audio-Visual Speech Recognition","url":"/task/audio-visual-speech-recognition","datasets_with_task":"/datasets/task/audio-visual-speech-recognition"},{"name":"Visual Keyword Spotting","url":"/task/visual-keyword-spotting","datasets_with_task":"/datasets/task/visual-keyword-spotting"},{"name":"Gesture Synchronization","url":"/task/gesture-synchronization","datasets_with_task":"/datasets/task/gesture-synchronization"}],"languages":[],"variants":["LRS3-TED"],"data_loaders":[],"num_papers_in_archive":63,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/lipreading-on-lrs3-ted","task":"Lipreading","dataset_variant":"LRS3-TED","rows":23,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"LP + Conformer","paper":"/paper/conformers-are-all-you-need-for-visual-speech","metrics":{"Word Error Rate (WER)":"12.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrs3-ted","task":"Audio-Visual Speech Recognition","dataset_variant":"LRS3-TED","rows":12,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"MMS-LLaMA","paper":"/paper/mms-llama-efficient-llm-based-audio-visual-1","metrics":{"Word Error Rate (WER)":"0.74"},"code_links":[{"title":"JeongHun0716/MMS-LLaMA","url":"https://github.com/JeongHun0716/MMS-LLaMA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-lrs3-ted","task":"Speech Recognition","dataset_variant":"LRS3-TED","rows":4,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"Whisper","paper":"/paper/whisper-flamingo-integrating-visual-features","metrics":{"Word Error Rate (WER)":"0.68"},"code_links":[{"title":"roudimit/whisper-flamingo","url":"https://github.com/roudimit/whisper-flamingo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-speech-recognition-on-lrs3-ted","task":"Visual Speech Recognition","dataset_variant":"LRS3-TED","rows":3,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"CTC/Attention","paper":"/paper/auto-avsr-audio-visual-speech-recognition","metrics":{"Word Error Rate (WER)":"19.1"},"code_links":[{"title":"mpc001/auto_avsr","url":"https://github.com/mpc001/auto_avsr"},{"title":"umbertocappellazzo/llama-avsr","url":"https://github.com/umbertocappellazzo/llama-avsr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/automatic-speech-recognition-asr-on-lrs3-ted","task":"Automatic Speech Recognition (ASR)","dataset_variant":"LRS3-TED","rows":2,"metrics":["WER","Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"DistillAV","paper":"/paper/audio-visual-representation-learning-via","metrics":{"WER":"1.4"},"code_links":[{"title":"jxzhanggg/DistillAV","url":"https://github.com/jxzhanggg/DistillAV"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/active-speaker-detection-on-lrs3-ted","task":"Active Speaker Detection","dataset_variant":"LRS3-TED","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GestSync","paper":"/paper/gestsync-determining-who-is-speaking-without","metrics":{"Accuracy":"87 %"},"code_links":[{"title":"Sindhu-Hegde/gestsync","url":"https://github.com/Sindhu-Hegde/gestsync"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-keyword-spotting-on-lrs3-ted","task":"Visual Keyword Spotting","dataset_variant":"LRS3-TED","rows":1,"metrics":["Top-1 Accuracy","Top-5 Accuracy","mAP","mAP IOU@0.5"],"first_row_in_archive_order":{"model":"Transpotter","paper":"/paper/visual-keyword-spotting-with-attention","metrics":{"Top-1 Accuracy":"52","Top-5 Accuracy":"77.1","mAP":"55.4","mAP IOU@0.5":"53.6"},"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":26,"of":26,"counts":{"papers_with_a_benchmark_row":26,"with_a_code_link":20,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":26,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/unified-speech-recognition-a-single-model-for","slug":"unified-speech-recognition-a-single-model-for","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","date":"2024-11-04","arxiv_id":"2411.02256","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":9,"official":{"repos":["ahaliassos/usr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-speech-recognition-a-single-model-for#ran","syntology_url":"https://syntology.ai/paper/2411.02256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02256"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":2,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":12,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"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":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":18,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":2,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":12,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/gestsync-determining-who-is-speaking-without","slug":"gestsync-determining-who-is-speaking-without","title":"GestSync: Determining who is speaking without a talking head","date":"2023-10-08","arxiv_id":"2310.05304","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/conformers-are-all-you-need-for-visual-speech","slug":"conformers-are-all-you-need-for-visual-speech","title":"Conformers are All You Need for Visual Speech Recognition","date":"2023-02-17","arxiv_id":"2302.10915","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-speech-recognition-for-multiple","slug":"visual-speech-recognition-for-multiple","title":"Visual Speech Recognition for Multiple Languages in the Wild","date":"2022-02-26","arxiv_id":"2202.13084","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/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","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":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"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/sub-word-level-lip-reading-with-visual","slug":"sub-word-level-lip-reading-with-visual","title":"Sub-word Level Lip Reading With Visual Attention","date":"2021-10-14","arxiv_id":"2110.07603","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"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":2,"code_links":2,"syntology":null},{"paper":"/paper/asr-is-all-you-need-cross-modal-distillation","slug":"asr-is-all-you-need-cross-modal-distillation","title":"ASR is all you need: cross-modal distillation for lip reading","date":"2019-11-28","arxiv_id":"1911.12747","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/spatio-temporal-fusion-based-convolutional","slug":"spatio-temporal-fusion-based-convolutional","title":"Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading","date":"2019-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/large-scale-visual-speech-recognition","slug":"large-scale-visual-speech-recognition","title":"Large-Scale Visual Speech Recognition","date":"2018-07-13","arxiv_id":"1807.05162","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/unified-speech-recognition-a-single-model-for","slug":"unified-speech-recognition-a-single-model-for","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","date":"2024-11-04","arxiv_id":"2411.02256","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":9,"official":{"repos":["ahaliassos/usr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-speech-recognition-a-single-model-for#ran","syntology_url":"https://syntology.ai/paper/2411.02256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02256"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":2,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":12,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"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":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":18,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":2,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":12,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/gestsync-determining-who-is-speaking-without","slug":"gestsync-determining-who-is-speaking-without","title":"GestSync: Determining who is speaking without a talking head","date":"2023-10-08","arxiv_id":"2310.05304","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/conformers-are-all-you-need-for-visual-speech","slug":"conformers-are-all-you-need-for-visual-speech","title":"Conformers are All You Need for Visual Speech Recognition","date":"2023-02-17","arxiv_id":"2302.10915","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-speech-recognition-for-multiple","slug":"visual-speech-recognition-for-multiple","title":"Visual Speech Recognition for Multiple Languages in the Wild","date":"2022-02-26","arxiv_id":"2202.13084","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/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","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":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"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/sub-word-level-lip-reading-with-visual","slug":"sub-word-level-lip-reading-with-visual","title":"Sub-word Level Lip Reading With Visual Attention","date":"2021-10-14","arxiv_id":"2110.07603","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"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":2,"code_links":2,"syntology":null},{"paper":"/paper/asr-is-all-you-need-cross-modal-distillation","slug":"asr-is-all-you-need-cross-modal-distillation","title":"ASR is all you need: cross-modal distillation for lip reading","date":"2019-11-28","arxiv_id":"1911.12747","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/spatio-temporal-fusion-based-convolutional","slug":"spatio-temporal-fusion-based-convolutional","title":"Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading","date":"2019-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/large-scale-visual-speech-recognition","slug":"large-scale-visual-speech-recognition","title":"Large-Scale Visual Speech Recognition","date":"2018-07-13","arxiv_id":"1807.05162","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/dataset/lrs3-ted/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/lrs3-ted/papers/ran/1","json":"/dataset/lrs3-ted/papers/ran/1.json","rows":6}],"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":6,"samples_harvested":58,"samples_ran":37,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":54,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":6,"papers_with_a_run_with_no_instrument_failure":5,"papers_where_every_run_was_an_instrument_failure":1,"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":"a2b56c9f05b90583333e61763270084c98df2c9e55fdaca1a32a8d8a4758ebc6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}