{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:40:19Z","timestamp":1773247219254,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389681","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction"],"prefix":"10.1109","author":[{"given":"Kailai","family":"Shen","sequence":"first","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diqun","family":"Yan","sequence":"additional","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Dong","sequence":"additional","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Ren","sequence":"additional","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxun","family":"Wu","sequence":"additional","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Hu","sequence":"additional","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2011.942469"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10766"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISRITI56927.2022.10053006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205757"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU57964.2023.10389671","volume-title":"The Singing Voice Conversion Challenge 2023","author":"Huang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-105"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11247"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10262"},{"key":"ref16","first-page":"12449","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":"ref17","article-title":"SSAST: Self-supervised audio spectrogram transformer","author":"Gong","year":"2021","journal-title":"arXiv preprint arXiv:2110.09784"},{"key":"ref18","volume-title":"Neural turing machines","author":"Graves","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX51781.2021.9465384"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref22","article-title":"The blizzard challenge 2019","volume-title":"Proc. Blizzard ChallengeWorkshop","volume":"2019","author":"Wu"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389681.pdf?arnumber=10389681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:53:43Z","timestamp":1706028823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389681","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}