{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:19:36Z","timestamp":1774419576915,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889835","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Weak-to-Strong Generalization in Speech Recognition"],"prefix":"10.1109","author":[{"given":"Soheil","family":"Khorram","sequence":"first","affiliation":[{"name":"Google,United States"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google,United States"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[{"name":"Google,United States"}]},{"given":"Kartik","family":"Audhkhasi","sequence":"additional","affiliation":[{"name":"Google,United States"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google,United States"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.03.005"},{"key":"ref3","article-title":"Weak-to-strong generalization: Eliciting strong capabilities with weak supervision","author":"Burns","year":"2023"},{"key":"ref4","article-title":"Improving weak-to-strong generalization with reliability-aware alignment","author":"Guo","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462037"},{"key":"ref8","article-title":"Self-taught recognizer: Toward unsupervised adaptation for speech foundation models","author":"Hu","year":"2024"},{"key":"ref9","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.01.023"},{"key":"ref11","article-title":"Co-supervised learning: Improving weak-to-strong generalization with hierarchical mixture of experts","author":"Liu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3071662"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095704"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11034"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-1190"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022581"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446985"},{"key":"ref20","article-title":"Google\u2019s privacy principles","volume-title":"Use the following link to access"},{"key":"ref21","article-title":"Artificial intelligence at google: Our principles"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref23","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096978"},{"key":"ref26","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747355"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889835.pdf?arnumber=10889835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:36Z","timestamp":1774416216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889835","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}