{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/lrs3-ted-a-large-scale-dataset-for-visual","title":"LRS3-TED: a large-scale dataset for visual speech recognition","arxiv_id":"1809.00496","date":"2018-09-03","proceeding":null,"authors":["Triantafyllos Afouras","Joon Son Chung","Andrew Zisserman"],"abstract":"This paper introduces a new multi-modal dataset for visual and audio-visual\nspeech recognition. It includes face tracks from over 400 hours of TED and TEDx\nvideos, along with the corresponding subtitles and word alignment boundaries.\nThe new dataset is substantially larger in scale compared to other public\ndatasets that are available for general research.","url_abs":"http://arxiv.org/abs/1809.00496v2","url_pdf":"http://arxiv.org/pdf/1809.00496v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lrs3-ted-a-large-scale-dataset-for-visual","repo_url":"https://github.com/jaejunl/hyface","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"audio-visual-speech-recognition","task_name":"Audio-Visual Speech Recognition"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"visual-speech-recognition","task_name":"Visual Speech Recognition"},{"task_slug":"word-alignment","task_name":"Word Alignment"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[{"slug":"lrs3-ted","name":"LRS3-TED","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.00496","atlas_url":"https://app.syntology.ai/?focus=1809.00496","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}