{"url":"/task/lip-to-speech-synthesis","name":"Lip to Speech Synthesis","slug":"lip-to-speech-synthesis","description_markdown":"Given a silent video of a speaker, generate the corresponding speech that matches the lip movements.","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":13,"papers_with_code":6,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/lip-to-speech-synthesis-on-lrw","slug":"lip-to-speech-synthesis-on-lrw","dataset":"LRW","dataset_url":"/dataset/lrw","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/lrw","name":"LRW","full_name":"Lip Reading in the Wild","num_papers_in_archive":188},{"url":"/dataset/glips","name":"GLips","full_name":"German Lips","num_papers_in_archive":6}],"subtasks":[{"url":"/task/speaker-specific-lip-to-speech-synthesis","name":"Speaker-Specific Lip to Speech Synthesis"}],"parent_tasks":[{"url":"/task/visual-speech-recognition","name":"Visual Speech Recognition"}],"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":6,"of":6,"tagged_in_all":13,"items":[{"url":"/paper/lip-to-speech-synthesis-in-the-wild-with","title":"Lip-to-Speech Synthesis in the Wild with Multi-task Learning","date":"2023-02-17","arxiv_id":"2302.08841","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/intelligible-lip-to-speech-synthesis-with","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","date":"2023-05-31","arxiv_id":"2305.19603","repositories_listed":2,"syntology":null},{"url":"/paper/fastlts-non-autoregressive-end-to-end","title":"FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis","date":"2022-07-08","arxiv_id":"2207.03800","repositories_listed":1,"syntology":null},{"url":"/paper/show-me-your-face-and-i-ll-tell-you-how-you","title":"Show Me Your Face, And I'll Tell You How You Speak","date":"2022-06-28","arxiv_id":"2206.14009","repositories_listed":1,"syntology":null},{"url":"/paper/lip-to-speech-synthesis-with-visual-context-1","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","date":"2022-04-04","arxiv_id":"2204.01726","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"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":3,"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"}}