{"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":"/paper/visual-speech-recognition-for-multiple","title":"Visual Speech Recognition for Multiple Languages in the Wild","arxiv_id":"2202.13084","date":"2022-02-26","proceeding":null,"authors":["Pingchuan Ma","Stavros Petridis","Maja Pantic"],"abstract":"Visual speech recognition (VSR) aims to recognize the content of speech based on lip movements, without relying on the audio stream. Advances in deep learning and the availability of large audio-visual datasets have led to the development of much more accurate and robust VSR models than ever before. However, these advances are usually due to the larger training sets rather than the model design. Here we demonstrate that designing better models is equally as important as using larger training sets. We propose the addition of prediction-based auxiliary tasks to a VSR model, and highlight the importance of hyperparameter optimization and appropriate data augmentations. We show that such a model works for different languages and outperforms all previous methods trained on publicly available datasets by a large margin. It even outperforms models that were trained on non-publicly available datasets containing up to to 21 times more data. We show, furthermore, that using additional training data, even in other languages or with automatically generated transcriptions, results in further improvement.","url_abs":"https://arxiv.org/abs/2202.13084v2","url_pdf":"https://arxiv.org/pdf/2202.13084v2.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":"visual-speech-recognition-for-multiple","repo_url":"https://github.com/mpc001/Visual_Speech_Recognition_for_Multiple_Languages","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"visual-speech-recognition-for-multiple","repo_url":"https://github.com/david-gimeno/lip-rtve","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"lipreading","task_name":"Lipreading"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"visual-speech-recognition","task_name":"Visual Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lipreading-on-cmlr","task":"Lipreading","dataset":"CMLR","model":"CTC/Attention","rank_in_archive_order":1,"of":5,"metrics":{"CER":"9.1%"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-grid-corpus-mixed-speech","task":"Lipreading","dataset":"GRID corpus (mixed-speech)","model":"CTC/Attention","rank_in_archive_order":1,"of":5,"metrics":{"Word Error Rate (WER)":"1.2"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"CTC/Attention (LRW+LRS2/3+AVSpeech)","rank_in_archive_order":7,"of":25,"metrics":{"Word Error Rate (WER)":"25.5"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"CTC/Attention","rank_in_archive_order":15,"of":25,"metrics":{"Word Error Rate (WER)":"32.9"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-lrs3-ted","task":"Lipreading","dataset":"LRS3-TED","model":"CTC/Attention (LRW+LRS2/3+AVSpeech)","rank_in_archive_order":13,"of":23,"metrics":{"Word Error Rate (WER)":"31.5"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.13084","atlas_url":"https://app.syntology.ai/?focus=2202.13084","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2202.13084"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2202.13084\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2202.13084"},"call":"get_concepts_for_paper(arxiv_id=\"2202.13084\")"}],"by_repo":[{"repo":"mpc001/Visual_Speech_Recognition_for_Multiple_Languages","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"david-gimeno/lip-rtve","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e215d497d733736b60e994e7f686a877ece96e0a89fd46f877225162ebacbaa0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}