{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T18:26:06Z","timestamp":1779906366879,"version":"3.53.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832315","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"818-824","source":"Crossref","is-referenced-by-count":33,"title":["The T05 System for the voicemos challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech"],"prefix":"10.1109","author":[{"given":"Kaito","family":"Baba","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wataru","family":"Nakata","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1878"},{"key":"ref5","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. ICML","author":"Ju"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1076"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/asru57964.2023.10389763"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389788"},{"key":"ref11","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2857"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW.2017.8272618"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2008-1"},{"key":"ref19","first-page":"1","article-title":"The Blizzard Challenge 2009","volume-title":"Proc. Blizzard Challenge Workshop","author":"Black"},{"key":"ref20","article-title":"The Blizzard Challenge 2010","volume-title":"Proc. Blizzard Challenge Workshop","author":"Black"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2011-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10922"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref24","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref25","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref28","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref29","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.132"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00125"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832315.pdf?arnumber=10832315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:11:48Z","timestamp":1737101508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832315","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}