{"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/pushing-the-limits-of-semi-supervised","title":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition","arxiv_id":"2010.10504","date":"2020-10-20","proceeding":null,"authors":["Yu Zhang","James Qin","Daniel S. Park","Wei Han","Chung-Cheng Chiu","Ruoming Pang","Quoc V. Le","Yonghui Wu"],"abstract":"We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabeled audio of the Libri-Light dataset. More precisely, we carry out noisy student training with SpecAugment using giant Conformer models pre-trained using wav2vec 2.0 pre-training. By doing so, we are able to achieve word-error-rates (WERs) 1.4%/2.6% on the LibriSpeech test/test-other sets against the current state-of-the-art WERs 1.7%/3.3%.","url_abs":"https://arxiv.org/abs/2010.10504v2","url_pdf":"https://arxiv.org/pdf/2010.10504v2.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":"pushing-the-limits-of-semi-supervised","repo_url":"https://github.com/tuanio/noisy-student-training-asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"noisy-student","method_name":"Noisy Student"},{"method_slug":"randaugment","method_name":"RandAugment"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Conformer + Wav2vec 2.0 + SpecAugment-based Noisy Student Training with Libri-Light","rank_in_archive_order":4,"of":64,"metrics":{"Word Error Rate (WER)":"1.4"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Conformer + Wav2vec 2.0 + SpecAugment-based Noisy Student Training with Libri-Light","rank_in_archive_order":4,"of":53,"metrics":{"Word Error Rate (WER)":"2.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.10504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10504"}},"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/tuanio/noisy-student-training-asr","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"ab8ba068813fcec5","entry":"count_params","repo":"tuanio/noisy-student-training-asr","repo_kind":"listed","path":"training_student_ctc.py","file_url":"https://github.com/tuanio/noisy-student-training-asr/blob/HEAD/training_student_ctc.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab8ba068813fcec5"}},{"code_sha256_prefix":"e6b1222247991890","entry":"save_state_dict","repo":"tuanio/noisy-student-training-asr","repo_kind":"listed","path":"training_student_ctc.py","file_url":"https://github.com/tuanio/noisy-student-training-asr/blob/HEAD/training_student_ctc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e6b1222247991890"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}