{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:48:07Z","timestamp":1784213287848,"version":"3.55.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746395","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8442-8446","source":"Crossref","is-referenced-by-count":116,"title":["Generalization Ability of MOS Prediction Networks"],"prefix":"10.1109","author":[{"given":"Erica","family":"Cooper","sequence":"first","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"BABEL: IARPA solicitation IARPA-BAA-11-02","author":"harper","year":"2011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref31","article-title":"The Fisher Corpus: a resource for the next generations of speech-to-text","author":"cieri","year":"2004","journal-title":"Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2010-1","article-title":"The Blizzard Challenge 2010","author":"king","year":"2010"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2011-1","article-title":"The Blizzard Challenge 2011","author":"king","year":"2011"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2013-1","article-title":"The Blizzard Challenge 2013","author":"king","year":"2013"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2016-1","article-title":"The Blizzard Challenge 2016","author":"king","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1331"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-14"},{"key":"ref18","first-page":"99","article-title":"Predictions of subjective ratings and spoofing assessments of Voice Conversion Challenge 2020 submissions","author":"kumar das","year":"2020","journal-title":"Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref29","first-page":"4218","article-title":"Common Voice: a massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"Proceedings of the 12th Language Resources and Evaluation Conference"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-32"},{"key":"ref8","article-title":"The Blizzard Challenge 2008","author":"karaiskos","year":"2008","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref9","first-page":"1","article-title":"The Blizzard Challenge 2009","author":"black","year":"2009","journal-title":"Proc Blizzard Challenge"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref23","article-title":"The blizzard challenge 2019","volume":"2019","author":"wu","year":"2019","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref25","article-title":"XIMERA: A new TTS from ATR based on corpus-based technologies","author":"kawai","year":"2004","journal-title":"Fifth ISCA workshop on speech synthesis"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746395.pdf?arnumber=9746395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:20:52Z","timestamp":1727061652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746395","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}