{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:00Z","timestamp":1775229900635,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413973","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"7068-7072","source":"Crossref","is-referenced-by-count":19,"title":["Non-Autoregressive Sequence-To-Sequence Voice Conversion"],"prefix":"10.1109","author":[{"given":"Tomoki","family":"Hayashi","sequence":"first","affiliation":[{"name":"TARVO Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"TARVO Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"Proc ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref32","author":"hayashi","year":"2020","journal-title":"kan-bayashi\/NonARSeq2SeqVC"},{"key":"ref31","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref12","article-title":"ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion","author":"kameoka","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682380"},{"key":"ref14","article-title":"Voice transformer network: Sequence-to-sequence voice conversion using transformer with text-to-speech pre-training","author":"huang","year":"2019"},{"key":"ref15","article-title":"Many-to-many voice transformer network","author":"kameoka","year":"2020"},{"key":"ref16","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref17","article-title":"Parallel neural text-to-speech","author":"peng","year":"2019"},{"key":"ref18","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref19","article-title":"Fast-Speech 2: Fast and high-quality end-to-end text-to-speech","author":"ren","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1419"},{"key":"ref27","first-page":"109","article-title":"Rapid F0 estimation for high-SNR speech based on fundamental component extraction","volume":"93","author":"morise","year":"2010","journal-title":"IEICE Trans Information Ans Systems"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"2162","DOI":"10.21437\/Interspeech.2010-596","article-title":"Applying voice conversion to concatenative singing-voice synthesis","author":"villavicencio","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref29","author":"hayashi","year":"2019","journal-title":"kan-bayashi\/ParallelWaveGAN"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"94","DOI":"10.21437\/Interspeech.2012-34","article-title":"Implementation of computationally efficient real-time voice conversion","author":"toda","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref7","first-page":"2514","article-title":"Statistical singing voice conversion with direct waveform modification based on the spectrum differential","author":"kobayashi","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1250\/ast.27.349"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032186"},{"key":"ref20","article-title":"FastPitch: Parallel text-to-speech with pitch prediction","author":"la?cucki","year":"2020"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref24","article-title":"Searching for activation functions","author":"ramachandran","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref26","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413973.pdf?arnumber=9413973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T03:30:26Z","timestamp":1672111826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413973","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}