{"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/leveraging-uni-modal-self-supervised-learning-1","title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition","arxiv_id":"2203.07996","date":"2022-02-24","proceeding":"ACL 2022 5","authors":["Xichen Pan","Peiyu Chen","Yichen Gong","Helong Zhou","Xinbing Wang","Zhouhan Lin"],"abstract":"Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the multimodal AVSR. In particular, audio and visual front-ends are trained on large-scale unimodal datasets, then we integrate components of both front-ends into a larger multimodal framework which learns to recognize parallel audio-visual data into characters through a combination of CTC and seq2seq decoding. We show that both components inherited from unimodal self-supervised learning cooperate well, resulting in that the multimodal framework yields competitive results through fine-tuning. Our model is experimentally validated on both word-level and sentence-level tasks. Especially, even without an external language model, our proposed model raises the state-of-the-art performances on the widely accepted Lip Reading Sentences 2 (LRS2) dataset by a large margin, with a relative improvement of 30%.","url_abs":"https://arxiv.org/abs/2203.07996v2","url_pdf":"https://arxiv.org/pdf/2203.07996v2.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":"leveraging-uni-modal-self-supervised-learning-1","repo_url":"https://github.com/lumia-group/leveraging-self-supervised-learning-for-avsr","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":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"lip-reading","task_name":"Lip Reading"},{"task_slug":"lipreading","task_name":"Lipreading"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"sentence","task_name":"Sentence"},{"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-lrs2","task":"Audio-Visual Speech Recognition","dataset":"LRS2","model":"MoCo + wav2vec (w/o extLM)","rank_in_archive_order":3,"of":8,"metrics":{"Test WER":"2.6"},"uses_additional_data":false},{"leaderboard":"/sota/automatic-speech-recognition-on-lrs2","task":"Automatic Speech Recognition (ASR)","dataset":"LRS2","model":"MoCo + wav2vec (w/o extLM)","rank_in_archive_order":3,"of":9,"metrics":{"Test WER":"2.7"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"MoCo + wav2vec (w/o extLM)","rank_in_archive_order":17,"of":25,"metrics":{"Word Error Rate (WER)":"43.2"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-lip-reading-in-the-wild","task":"Lipreading","dataset":"Lip Reading in the Wild","model":"MoCo + Wav2Vec by SJTU LUMIA","rank_in_archive_order":14,"of":22,"metrics":{"Top-1 Accuracy":"85.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.07996","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07996"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lumia-group/leveraging-self-supervised-learning-for-avsr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"04af7ca817c65533","entry":"crop_patch","repo":"lumia-group/leveraging-self-supervised-learning-for-avsr","repo_kind":"official","path":"preprocess/preprocessing.py","file_url":"https://github.com/lumia-group/leveraging-self-supervised-learning-for-avsr/blob/HEAD/preprocess/preprocessing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04af7ca817c65533"}},{"code_sha256_prefix":"96bde5c83493b6bb","entry":"cut_patch","repo":"lumia-group/leveraging-self-supervised-learning-for-avsr","repo_kind":"official","path":"preprocess/preprocessing.py","file_url":"https://github.com/lumia-group/leveraging-self-supervised-learning-for-avsr/blob/HEAD/preprocess/preprocessing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96bde5c83493b6bb"}},{"code_sha256_prefix":"693dceead2019125","entry":"generate_square_subsequent_mask","repo":"lumia-group/leveraging-self-supervised-learning-for-avsr","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/lumia-group/leveraging-self-supervised-learning-for-avsr/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"693dceead2019125"}},{"code_sha256_prefix":"cb52c4993e0435d8","entry":"get_files","repo":"lumia-group/leveraging-self-supervised-learning-for-avsr","repo_kind":"official","path":"saveh5.py","file_url":"https://github.com/lumia-group/leveraging-self-supervised-learning-for-avsr/blob/HEAD/saveh5.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb52c4993e0435d8"}},{"code_sha256_prefix":"5b77efeb5cecfa7b","entry":"preprocess_sample","repo":"lumia-group/leveraging-self-supervised-learning-for-avsr","repo_kind":"official","path":"preprocess/find_mean.py","file_url":"https://github.com/lumia-group/leveraging-self-supervised-learning-for-avsr/blob/HEAD/preprocess/find_mean.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b77efeb5cecfa7b"}},{"code_sha256_prefix":"f3a5a2d37d6e8b20","entry":"shape_to_array","repo":"lumia-group/leveraging-self-supervised-learning-for-avsr","repo_kind":"official","path":"preprocess/find_mean.py","file_url":"https://github.com/lumia-group/leveraging-self-supervised-learning-for-avsr/blob/HEAD/preprocess/find_mean.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3a5a2d37d6e8b20"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}