{"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/es3-evolving-self-supervised-learning-of","title":"ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations","arxiv_id":null,"date":"2024-01-01","proceeding":"CVPR 2024 1","authors":["Yuanhang Zhang","Shuang Yang","Shiguang Shan","Xilin Chen"],"abstract":"    We propose a novel strategy ES3 for self-supervised learning of robust audio-visual speech representations from unlabeled talking face videos. While many recent approaches for this task primarily rely on guiding the learning process using the audio modality alone to capture information shared between audio and video we reframe the problem as the acquisition of shared unique (modality-specific) and synergistic speech information to address the inherent asymmetry between the modalities. Based on this formulation we propose a novel \"evolving\" strategy that progressively builds joint audio-visual speech representations that are strong for both uni-modal (audio & visual) and bi-modal (audio-visual) speech. First we leverage the more easily learnable audio modality to initialize audio and visual representations by capturing audio-unique and shared speech information. Next we incorporate video-unique speech information and bootstrap the audio-visual representations on top of the previously acquired shared knowledge. Finally we maximize the total audio-visual speech information including synergistic information to obtain robust and comprehensive representations. We implement ES3 as a simple Siamese framework and experiments on both English benchmarks and a newly contributed large-scale Mandarin dataset show its effectiveness. In particular on LRS2-BBC our smallest model is on par with SoTA models with only 1/2 parameters and 1/8 unlabeled data (223h).    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2024/html/Zhang_ES3_Evolving_Self-Supervised_Learning_of_Robust_Audio-Visual_Speech_Representations_CVPR_2024_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2024/papers/Zhang_ES3_Evolving_Self-Supervised_Learning_of_Robust_Audio-Visual_Speech_Representations_CVPR_2024_paper.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":[],"tasks":[{"task_slug":"audio-visual-speech-recognition","task_name":"Audio-Visual Speech Recognition"},{"task_slug":"lipreading","task_name":"Lipreading"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[],"datasets_introduced":[{"slug":"cas-vsr-s101","name":"CAS-VSR-S101","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-visual-speech-recognition-on-cas-vsr","task":"Audio-Visual Speech Recognition","dataset":"CAS-VSR-S101","model":"ES³ Base*","rank_in_archive_order":1,"of":1,"metrics":{"Word Error Rate (WER)":"11.0"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-cas-vsr-s101","task":"Lipreading","dataset":"CAS-VSR-S101","model":"ES³ Base*","rank_in_archive_order":1,"of":1,"metrics":{"Word Error Rate (WER)":"55.6"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"ES³ Large + extLM","rank_in_archive_order":6,"of":25,"metrics":{"Word Error Rate (WER)":"24.6"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"ES³ Large","rank_in_archive_order":8,"of":25,"metrics":{"Word Error Rate (WER)":"26.7"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"ES³ Base + extLM","rank_in_archive_order":9,"of":25,"metrics":{"Word Error Rate (WER)":"28.7"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"ES³ Base* + extLM","rank_in_archive_order":12,"of":25,"metrics":{"Word Error Rate (WER)":"29.3"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"ES³ Base","rank_in_archive_order":13,"of":25,"metrics":{"Word Error Rate (WER)":"30.7"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"ES³ Base*","rank_in_archive_order":14,"of":25,"metrics":{"Word Error Rate (WER)":"31.4"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-lrs3-ted","task":"Lipreading","dataset":"LRS3-TED","model":"ES³ Large","rank_in_archive_order":15,"of":23,"metrics":{"Word Error Rate (WER)":"37.1"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-lrs3-ted","task":"Lipreading","dataset":"LRS3-TED","model":"ES³ Base","rank_in_archive_order":16,"of":23,"metrics":{"Word Error Rate (WER)":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-cas-vsr-s101","task":"Speech Recognition","dataset":"CAS-VSR-S101","model":"ES³ Base*","rank_in_archive_order":1,"of":1,"metrics":{"Word Error Rate (WER)":"11.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4dff7dd9f3af536fe428a110d7c0374dbc10fb6f6f09b0d68f33a545f6e62922","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}