{"url":"/task/speaker-specific-lip-to-speech-synthesis","name":"Speaker-Specific Lip to Speech Synthesis","slug":"speaker-specific-lip-to-speech-synthesis","description_markdown":"How accurately can we infer an individual’s speech style and content from his/her lip movements? [1]\r\n\r\nIn this task, the model is trained on a specific speaker, or a very limited set of speakers. \r\n\r\n[1] Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis, CVPR 2020.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":3,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on","slug":"speaker-specific-lip-to-speech-synthesis-on","dataset":"GRID corpus (mixed-speech)","dataset_url":"/dataset/grid","rows_in_archive":2,"metrics":["ESTOI","PESQ","STOI"],"first_row_in_archive_order":{"model":"Visual Voice Memory","paper_title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","paper_url":"/paper/speech-reconstruction-with-reminiscent-sound","paper_date":"2021-11-17","arxiv_id":null,"code_links":[{"title":"joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","url":"https://github.com/joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory"}],"syntology":null}},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-3","slug":"speaker-specific-lip-to-speech-synthesis-on-3","dataset":"Lip2Wav (EH)","dataset_url":null,"rows_in_archive":2,"metrics":["ESTOI","PESQ","STOI"],"first_row_in_archive_order":{"model":"Visual Voice Memory","paper_title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","paper_url":"/paper/speech-reconstruction-with-reminiscent-sound","paper_date":"2021-11-17","arxiv_id":null,"code_links":[{"title":"joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","url":"https://github.com/joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory"}],"syntology":null}},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-4","slug":"speaker-specific-lip-to-speech-synthesis-on-4","dataset":"Lip2Wav (HS)","dataset_url":null,"rows_in_archive":2,"metrics":["ESTOI","PESQ","STOI"],"first_row_in_archive_order":{"model":"Visual Voice Memory","paper_title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","paper_url":"/paper/speech-reconstruction-with-reminiscent-sound","paper_date":"2021-11-17","arxiv_id":null,"code_links":[{"title":"joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","url":"https://github.com/joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory"}],"syntology":null}},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-5","slug":"speaker-specific-lip-to-speech-synthesis-on-5","dataset":"Lip2Wav (DL)","dataset_url":null,"rows_in_archive":2,"metrics":["ESTOI","PESQ","STOI"],"first_row_in_archive_order":{"model":"Visual Voice Memory","paper_title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","paper_url":"/paper/speech-reconstruction-with-reminiscent-sound","paper_date":"2021-11-17","arxiv_id":null,"code_links":[{"title":"joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","url":"https://github.com/joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory"}],"syntology":null}},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-6","slug":"speaker-specific-lip-to-speech-synthesis-on-6","dataset":"Lip2Wav (Chess)","dataset_url":null,"rows_in_archive":2,"metrics":["ESTOI","PESQ","STOI"],"first_row_in_archive_order":{"model":"Visual Voice Memory","paper_title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","paper_url":"/paper/speech-reconstruction-with-reminiscent-sound","paper_date":"2021-11-17","arxiv_id":null,"code_links":[{"title":"joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","url":"https://github.com/joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory"}],"syntology":null}},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-7","slug":"speaker-specific-lip-to-speech-synthesis-on-7","dataset":"Lip2Wav (Chem)","dataset_url":null,"rows_in_archive":2,"metrics":["ESTOI","PESQ","STOI"],"first_row_in_archive_order":{"model":"Visual Voice Memory","paper_title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","paper_url":"/paper/speech-reconstruction-with-reminiscent-sound","paper_date":"2021-11-17","arxiv_id":null,"code_links":[{"title":"joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","url":"https://github.com/joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory"}],"syntology":null}},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-1","slug":"speaker-specific-lip-to-speech-synthesis-on-1","dataset":"TCD-TIMIT corpus (mixed-speech)","dataset_url":"/dataset/timit","rows_in_archive":1,"metrics":["ESTOI","PESQ","STOI"],"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":1,"n_unverified":8,"n_pointer_only":0}}}],"datasets":[{"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}],"subtasks":[],"parent_tasks":[{"url":"/task/lip-to-speech-synthesis","name":"Lip to Speech Synthesis"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":3,"of":3,"tagged_in_all":4,"items":[{"url":"/paper/densely-connected-convolutional-networks","title":"Densely Connected Convolutional Networks","date":"2016-08-25","arxiv_id":"1608.06993","repositories_listed":146,"syntology":{"n":71,"n_ran":18,"n_unverified":53,"n_pointer_only":7}},{"url":"/paper/speech-reconstruction-with-reminiscent-sound","title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","date":"2021-11-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/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":1,"n_unverified":8,"n_pointer_only":0}}],"syntology_records":2,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}