{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:08:31Z","timestamp":1755839311361,"version":"3.37.3"},"reference-count":31,"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"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747533","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"906-910","source":"Crossref","is-referenced-by-count":6,"title":["MOS Predictor for Synthetic Speech with I-Vector Inputs"],"prefix":"10.1109","author":[{"given":"Miao","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shicong","family":"Li","sequence":"additional","affiliation":[{"name":"Xiaomi Inc,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Xiang","sequence":"additional","affiliation":[{"name":"Xiaomi Inc,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Yao","sequence":"additional","affiliation":[{"name":"Inner Mongolia University of Science and Technology,Baotou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lidong","family":"Yang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University of Science and Technology,Baotou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2307\/1422689"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2382"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2111"},{"article-title":"Neural mos prediction for synthesized speech using multi-task learning with spoofing detection and spoofing type classification","year":"2020","author":"choi","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-287"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-128"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015"},{"article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","year":"2019","author":"qian","key":"ref4"},{"key":"ref27","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"abs 1502 3167","author":"ioffe","year":"2015","journal-title":"CoRR"},{"article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","year":"2017","author":"kaneko","key":"ref3"},{"year":"0","key":"ref6","article-title":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/13.1.25"},{"year":"0","key":"ref5","article-title":"Methods for subjective determination of transmission quality"},{"year":"0","key":"ref8","article-title":"Single-ended method for objective speech quality assessment in narrow-band telephony applications"},{"year":"0","key":"ref7","article-title":"Perceptual objective listening quality prediction"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","article-title":"Wavenet: A generative model for raw audio","volume":"abs 1609 3499","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref9","article-title":"Automos: Learning a non-intrusive assessor of naturalness-of-speech","volume":"abs 1611 9207","author":"patton","year":"2016","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s41233-020-00036-z"},{"key":"ref22","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683175"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-488"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09747533.pdf?arnumber=9747533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:50Z","timestamp":1660594070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747533","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}