{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:34:09Z","timestamp":1767706449929,"version":"3.32.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800400","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"716-720","source":"Crossref","is-referenced-by-count":2,"title":["Ensemble Knowledge Distillation from Speech SSL Models Considering Inter-Teacher Differences"],"prefix":"10.1109","author":[{"given":"Pei-Jun","family":"Liao","sequence":"first","affiliation":[{"name":"College of Electrical Engineering and Computer Science, National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering and Computer Science, National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref2","article-title":"GLUE: A multitask benchmark and analysis platform for natural language understanding","volume-title":"Proc. ICLR","author":"Wang","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022399"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-612"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref8","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref13","article-title":"Ensemble knowledge distil-lation of self-supervised speech models","volume-title":"Proc. ICASSP","author":"Huang","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. ICML","author":"Baevski","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref18","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. NeurIPS","author":"Yang","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/APPEEC48164.2020.9220511"},{"key":"ref20","article-title":"wav2vec: Unsupervised pretraining for speech recognition","volume-title":"Proc. Inter-speech","author":"Schneider","year":"2019"},{"key":"ref21","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref23","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. ICLR","author":"Baevski","year":"2020"},{"key":"ref24","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. ICLR","author":"Lan","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1213"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688302"},{"key":"ref28","article-title":"One teacher is enough? pretrained language model distillation from multiple teachers","volume-title":"Proc. ACL-IJCNLP","author":"Wu","year":"2021"},{"key":"ref29","article-title":"Unified and effective ensemble knowledge distillation","author":"Wu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref32","article-title":"Speech Commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2396"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref35","article-title":"Snips Voice Platform: An embedded spoken language understanding system for private-by-design voice interfaces","author":"Coucke","year":"2018","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref37","article-title":"Lib-rispeech: An ASR corpus based on public domain audio books","volume-title":"Proc. ICASSP","author":"Panayotov","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800400.pdf?arnumber=10800400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:27Z","timestamp":1735021587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800400","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}