{"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/jointly-learning-visual-and-auditory-speech","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","arxiv_id":"2212.06246","date":"2022-12-12","proceeding":null,"authors":["Alexandros Haliassos","Pingchuan Ma","Rodrigo Mira","Stavros Petridis","Maja Pantic"],"abstract":"We present RAVEn, a self-supervised multi-modal approach to jointly learn visual and auditory speech representations. Our pre-training objective involves encoding masked inputs, and then predicting contextualised targets generated by slowly-evolving momentum encoders. Driven by the inherent differences between video and audio, our design is asymmetric w.r.t. the two modalities' pretext tasks: Whereas the auditory stream predicts both the visual and auditory targets, the visual one predicts only the auditory targets. We observe strong results in low- and high-resource labelled data settings when fine-tuning the visual and auditory encoders resulting from a single pre-training stage, in which the encoders are jointly trained. Notably, RAVEn surpasses all self-supervised methods on visual speech recognition (VSR) on LRS3, and combining RAVEn with self-training using only 30 hours of labelled data even outperforms a recent semi-supervised method trained on 90,000 hours of non-public data. At the same time, we achieve state-of-the-art results in the LRS3 low-resource setting for auditory speech recognition (as well as for VSR). Our findings point to the viability of learning powerful speech representations entirely from raw video and audio, i.e., without relying on handcrafted features. Code and models are available at https://github.com/ahaliassos/raven.","url_abs":"https://arxiv.org/abs/2212.06246v2","url_pdf":"https://arxiv.org/pdf/2212.06246v2.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":"jointly-learning-visual-and-auditory-speech","repo_url":"https://github.com/ahaliassos/raven","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-visual-speech-recognition","task_name":"Audio-Visual Speech Recognition"},{"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/audio-visual-speech-recognition-on-lrs3-ted","task":"Audio-Visual Speech Recognition","dataset":"LRS3-TED","model":"RAVEn Large","rank_in_archive_order":7,"of":12,"metrics":{"Word Error Rate (WER)":"1.4"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"RAVEn Large","rank_in_archive_order":4,"of":25,"metrics":{"Word Error Rate (WER)":"18.6"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs3-ted","task":"Lipreading","dataset":"LRS3-TED","model":"RAVEn Large","rank_in_archive_order":6,"of":23,"metrics":{"Word Error Rate (WER)":"23.4"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-lrs2","task":"Speech Recognition","dataset":"LRS2","model":"RAVEn Large","rank_in_archive_order":1,"of":1,"metrics":{"Word Error Rate (WER)":"2.1"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-lrs3-ted","task":"Speech Recognition","dataset":"LRS3-TED","model":"RAVEn Large","rank_in_archive_order":4,"of":4,"metrics":{"Word Error Rate (WER)":"1.4"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.06246","atlas_url":"https://app.syntology.ai/?focus=2212.06246","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":"2212.06246"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.06246\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.06246"},"call":"get_concepts_for_paper(arxiv_id=\"2212.06246\")"}],"by_repo":[{"repo":"ahaliassos/raven","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2404.02098"],"harvested_for_calls":[{"arxiv_id":"2404.02098","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.02098"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.02098\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"15e36845db05c833bb2f4302f924e7ed72061770b3c71feba26e6edf6d0483c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}