{"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/braven-improving-self-supervised-pre-training","title":"BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition","arxiv_id":"2404.02098","date":"2024-04-02","proceeding":null,"authors":["Alexandros Haliassos","Andreas Zinonos","Rodrigo Mira","Stavros Petridis","Maja Pantic"],"abstract":"Self-supervision has recently shown great promise for learning visual and auditory speech representations from unlabelled data. In this work, we propose BRAVEn, an extension to the recent RAVEn method, which learns speech representations entirely from raw audio-visual data. Our modifications to RAVEn enable BRAVEn to achieve state-of-the-art results among self-supervised methods in various settings. Moreover, we observe favourable scaling behaviour by increasing the amount of unlabelled data well beyond other self-supervised works. In particular, we achieve 20.0% / 1.7% word error rate for VSR / ASR on the LRS3 test set, with only 30 hours of labelled data and no external ASR models. Our results suggest that readily available unlabelled audio-visual data can largely replace costly transcribed data.","url_abs":"https://arxiv.org/abs/2404.02098v1","url_pdf":"https://arxiv.org/pdf/2404.02098v1.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":"braven-improving-self-supervised-pre-training","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":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.02098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02098"}},"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/ahaliassos/raven","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":10,"unverified":4},"by_repo_kind":{"official":{"samples":14,"ran":10,"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":"96ab9eba7ed25bc3","entry":"average_checkpoints","repo":"ahaliassos/raven","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96ab9eba7ed25bc3"}},{"code_sha256_prefix":"08b8264f1a3a1591","entry":"end_detect","repo":"ahaliassos/raven","repo_kind":"official","path":"espnet/nets/e2e_asr_common.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/espnet/nets/e2e_asr_common.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08b8264f1a3a1591"}},{"code_sha256_prefix":"15461a4fffed58aa","entry":"get_cer","repo":"ahaliassos/raven","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15461a4fffed58aa"}},{"code_sha256_prefix":"4f158e2aa3d314f9","entry":"get_er","repo":"ahaliassos/raven","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f158e2aa3d314f9"}},{"code_sha256_prefix":"02eb6bc0a23198cb","entry":"get_vgg2l_odim","repo":"ahaliassos/raven","repo_kind":"official","path":"espnet/nets/e2e_asr_common.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/espnet/nets/e2e_asr_common.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02eb6bc0a23198cb"}},{"code_sha256_prefix":"c0ed4f13d5339d56","entry":"get_wer","repo":"ahaliassos/raven","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0ed4f13d5339d56"}},{"code_sha256_prefix":"995e1b53bc619c6a","entry":"ids_to_str","repo":"ahaliassos/raven","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"995e1b53bc619c6a"}},{"code_sha256_prefix":"a6b0233b308d11ee","entry":"is_scipy_wav_style","repo":"ahaliassos/raven","repo_kind":"official","path":"espnet/utils/cli_utils.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/espnet/utils/cli_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6b0233b308d11ee"}},{"code_sha256_prefix":"076c0dd1245be79b","entry":"label_smoothing_dist","repo":"ahaliassos/raven","repo_kind":"official","path":"espnet/nets/e2e_asr_common.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/espnet/nets/e2e_asr_common.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"076c0dd1245be79b"}},{"code_sha256_prefix":"a322f4a71dff8cd9","entry":"strtobool","repo":"ahaliassos/raven","repo_kind":"official","path":"espnet/utils/cli_utils.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/espnet/utils/cli_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a322f4a71dff8cd9"}},{"code_sha256_prefix":"bb3665ddb6b8dd2d","entry":"adadelta_eps_decay","repo":"ahaliassos/raven","repo_kind":"official","path":"espnet/asr/asr_utils.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/espnet/asr/asr_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":"bb3665ddb6b8dd2d"}},{"code_sha256_prefix":"1fa5ca494ed9750a","entry":"adam_lr_decay","repo":"ahaliassos/raven","repo_kind":"official","path":"espnet/asr/asr_utils.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/espnet/asr/asr_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":"1fa5ca494ed9750a"}},{"code_sha256_prefix":"8b81ecb31057c782","entry":"get_param_groups","repo":"ahaliassos/raven","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"8b81ecb31057c782"}},{"code_sha256_prefix":"96081a60369c59e0","entry":"restore_snapshot","repo":"ahaliassos/raven","repo_kind":"official","path":"espnet/asr/asr_utils.py","file_url":"https://github.com/ahaliassos/raven/blob/HEAD/espnet/asr/asr_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":"96081a60369c59e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}