{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:03:16Z","timestamp":1775199796470,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434659","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Unifying Model and Layer Fusion for Speech Foundation Models"],"prefix":"10.1109","author":[{"given":"Yi-Jen","family":"Shih","sequence":"first","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref2","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201820.","author":"Baevski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proceedings of the 39th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"162","author":"Baevski"},{"key":"ref5","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Radford"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref8","article-title":"Unsupervised speech recognition","author":"Baevski","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10652"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022827"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022954"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096882"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1212"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/a:1022648800760"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1023\/A:1018054314350","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Machine Learning"},{"key":"ref19","first-page":"148","article-title":"Experiments with a new boosting algorithm","volume-title":"Proceedings of the Thirteenth International Conference on International Conference on Machine Learning, ser. ICML\u201996.","author":"Freund"},{"key":"ref20","article-title":"Exploring effective fusion algorithms for speech based self-supervised learning models","author":"Tang","year":"2022","journal-title":"NCMMSC2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1609"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10262"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389631"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2296"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-849"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-326"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11376"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2199"},{"key":"ref32","first-page":"1","article-title":"Resource-efficient transfer learning from speech foundation model using hierarchical feature fusion","volume-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Huo"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434659.pdf?arnumber=11434659","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:51Z","timestamp":1775192271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434659\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434659","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}