{"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/semi-supervised-speech-recognition-via-local","title":"Semi-Supervised Speech Recognition via Local Prior Matching","arxiv_id":"2002.10336","date":"2020-02-24","proceeding":null,"authors":["Wei-Ning Hsu","Ann Lee","Gabriel Synnaeve","Awni Hannun"],"abstract":"For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose local prior matching (LPM), a semi-supervised objective that distills knowledge from a strong prior (e.g. a language model) to provide learning signal to a discriminative model trained on unlabeled speech. We demonstrate that LPM is theoretically well-motivated, simple to implement, and superior to existing knowledge distillation techniques under comparable settings. Starting from a baseline trained on 100 hours of labeled speech, with an additional 360 hours of unlabeled data, LPM recovers 54% and 73% of the word error rate on clean and noisy test sets relative to a fully supervised model on the same data.","url_abs":"https://arxiv.org/abs/2002.10336v1","url_pdf":"https://arxiv.org/pdf/2002.10336v1.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":"semi-supervised-speech-recognition-via-local","repo_url":"https://github.com/facebookresearch/wav2letter","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"local-prior-matching","method_name":"LPM"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[{"slug":"local-prior-matching","name":"LPM","full_name":"Local Prior Matching"}],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Local Prior Matching (Large Model)","rank_in_archive_order":62,"of":64,"metrics":{"Word Error Rate (WER)":"7.19"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Local Prior Matching (Large Model, ConvLM LM)","rank_in_archive_order":51,"of":53,"metrics":{"Word Error Rate (WER)":"15.28"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Local Prior Matching (Large Model)","rank_in_archive_order":53,"of":53,"metrics":{"Word Error Rate (WER)":"20.84"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.10336","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}