{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:47Z","timestamp":1775230007132,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414348","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"76-80","source":"Crossref","is-referenced-by-count":17,"title":["Sequence-To-Sequence Singing Voice Synthesis With Perceptual Entropy Loss"],"prefix":"10.1109","author":[{"given":"Jiatong","family":"Shi","sequence":"first","affiliation":[]},{"given":"Shuai","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Nan","family":"Huo","sequence":"additional","affiliation":[]},{"given":"Yuekai","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Tohoku kiritan singing voice corpus","author":"moris","year":"0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref31","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.12.47"},{"key":"ref35","article-title":"A disciplined approach to neural network hyperparameters: Part 1–learning rate, batch size, momentum, and weight decay","author":"smith","year":"2018"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref10","article-title":"Singing voice synthesis based on convolutional neural networks","author":"nakamura","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053811"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683154"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903099"},{"key":"ref14","article-title":"Singing synthesis: with a little help from my attention","author":"angelini","year":"2019"},{"key":"ref15","article-title":"Score and lyrics-free singing voice generation","author":"liu","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053950"},{"key":"ref17","article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","author":"chen","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1789"},{"key":"ref28","first-page":"115","author":"jayant","year":"1984","journal-title":"Digital Coding of Waveforms Principles and Applications to Speech and Video"},{"key":"ref4","article-title":"Recent development of the hmm-based singing voice synthesis system—sinsy","author":"oura","year":"2010","journal-title":"Proc Seventh ISCA Workshop on Speech Synthesis"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app7121313"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/5.241504"},{"key":"ref5","article-title":"An hmm-based singing voice synthesis system","author":"saino","year":"2006","journal-title":"Proc Ninth International Conference on SLP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref2","article-title":"Vocaloid-commercial singing synthesizer based on sample concatenation","author":"kenmochi","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1575"},{"key":"ref1","article-title":"Concatenation-based midi-to-singing voice synthesis","author":"macon","year":"1997","journal-title":"Proc Audio Engineering Society Convention"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1724"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref21","article-title":"Bytesing: A chinese singing voice synthesis system using duration allocated encoderdecoder acoustic models and wavernn vocoders","author":"gu","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/49.608"},{"key":"ref25","article-title":"Learning singing from speech","author":"zhang","year":"2019"}],"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\/09414348.pdf?arnumber=9414348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:04Z","timestamp":1652197264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414348","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}