{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:09:43Z","timestamp":1775200183111,"version":"3.50.1"},"reference-count":46,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434750","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Distillation from Speech and Music Representation Models"],"prefix":"10.1109","author":[{"given":"Jui-Chiang","family":"Wei","sequence":"first","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Yi-Cheng","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Fabian","family":"Ritter-Gutierrez","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022770"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1722"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","article-title":"MERT: Acoustic music understanding model with large-scale self-supervised training","volume-title":"The Twelfth International Conference on Learning Representations","author":"LI"},{"key":"ref7","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref9","article-title":"Dynamic-superb phase-2: A collaboratively expanding benchmark for measuring the capabilities of spoken language models with 180 tasks","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv:2411.05361"},{"key":"ref10","volume-title":"Jukebox: A Generative Model for Music","author":"Dhariwal","year":"2020"},{"key":"ref11","volume-title":"Contrastive Learning of Musical Representations","author":"Spijkervet","year":"2021"},{"key":"ref12","volume-title":"Encodecmae: Leveraging neural codecs for universal audio representation learning","author":"Pepino","year":"2024"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2025-747","volume-title":"Distilling a speech and music encoder with task arithmetic","author":"Ritter-Gutierrez","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746790"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096445"},{"key":"ref16","article-title":"Theia: Distilling diverse vision foundation models for robot learning","volume-title":"8th Annual Conference on Robot Learning","author":"Shang"},{"key":"ref17","volume-title":"Ea-kd: Entropy-based adaptive knowledge distillation","author":"Su","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-432"},{"key":"ref19","article-title":"Distilling the knowledge in a neural network","volume-title":"NIPS 2014 Deep Learning Workshop","volume":"abs\/1503.02531","author":"Hinton"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2022-11112","article-title":"Fithubert: Going thinner and deeper for knowledge distillation of speech self-supervised learning","volume-title":"23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022","author":"Lee"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10269"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-454"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095480"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10627241"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022474"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/app13095630"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-636"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715031"},{"key":"ref30","article-title":"Multi-teacher knowledge distillation as an effective method for compressing ensembles of neural networks","author":"Zuchniak","year":"2023","journal-title":"arXiv preprint arXiv:2302.07215"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-072-4_068"},{"key":"ref32","article-title":"Multilingual neural machine translation with knowledge distillation","volume-title":"International Conference on Learning Representations","author":"Tan"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.387"},{"key":"ref34","article-title":"Unified and effective ensemble knowledge distillation","volume":"abs\/2204.00548","author":"Wu","year":"2022","journal-title":"ArXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688302"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-1190"},{"key":"ref37","article-title":"Knowledge distillation from multiple foundation models for end-to-end speech recognition","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2303.10917"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref40","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","volume":"abs\/1804.03209","author":"Warden","year":"2018","journal-title":"CoRR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref43","first-page":"468","article-title":"Vocalset: A singing voice dataset","author":"Wilkins","year":"2018","journal-title":"ISMIR"},{"key":"ref44","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International conference on machine learning","author":"Engel"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IWSSIP48289.2020.9145170"},{"key":"ref46","volume-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"}],"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\/11434750.pdf?arnumber=11434750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:17Z","timestamp":1775192357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434750","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}