{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:19:23Z","timestamp":1776881963217,"version":"3.51.2"},"reference-count":33,"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\/asru65441.2025.11433842","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Selection of Layers from Self-supervised Learning Models for Predicting Mean-Opinion-Score of Speech"],"prefix":"10.1109","author":[{"given":"Xinyu","family":"Liang","sequence":"first","affiliation":[{"name":"HCLTech AB,Sweden"}]},{"given":"Fredrik","family":"Cumlin","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science,Sweden"}]},{"given":"Victor","family":"Ungureanu","sequence":"additional","affiliation":[{"name":"Google LLC"}]},{"given":"Chandan K. A.","family":"Reddy","sequence":"additional","affiliation":[{"name":"Google LLC"}]},{"given":"Christian","family":"Sch\u00fcldt","sequence":"additional","affiliation":[{"name":"Google LLC"}]},{"given":"Saikat","family":"Chatterjee","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science,Sweden"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108183"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414878"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-478"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747222"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-299"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1436"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715351"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-518"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389788"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-105"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414321"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688093"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1823"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10597"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/13.1.25"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/1422689"},{"key":"ref29","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref32","article-title":"Poor man\u2019s bert: Smaller and faster transformer models","author":"Sajjad","year":"2020","journal-title":"arXiv preprint arXiv:2004.03844"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1280"}],"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\/11433842.pdf?arnumber=11433842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:54:43Z","timestamp":1775192083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11433842","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}