{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:40Z","timestamp":1775229760344,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"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":[[2021,1,24]]},"DOI":"10.1109\/iscslp49672.2021.9362104","type":"proceedings-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T18:37:05Z","timestamp":1614623825000},"page":"1-5","source":"Crossref","is-referenced-by-count":33,"title":["ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoders"],"prefix":"10.1109","author":[{"given":"Yu","family":"Gu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghui","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benlai","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jitong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep Voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2017"},{"key":"ref11","article-title":"Singing synthesis: with a little help from my attention","author":"angelini","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1722"},{"key":"ref13","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Durian: Duration informed attention network for multimodal synthesis","author":"yu","year":"2019"},{"key":"ref15","article-title":"Sequence-to-sequence singing synthesis using the feed-forward transformer","author":"blaauw","year":"2019"},{"key":"ref16","article-title":"Learning singing from speech","author":"zhang","year":"2019"},{"key":"ref17","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref18","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref6","article-title":"Singing voice synthesis based on convolutional neural networks","author":"nakamura","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref8","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 2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1575"},{"key":"ref2","article-title":"Recent development of the HMM-based singing voice synthesis system—Sinsy","author":"oura","year":"2010","journal-title":"Seventh ISCA Workshop on Speech Synthesis"},{"key":"ref1","article-title":"An HMM-based singing voice synthesis system","author":"saino","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1563"},{"key":"ref22","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"},{"key":"ref21","first-page":"9","article-title":"MusicXML in commercial applications","author":"good","year":"2006"},{"key":"ref24","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume":"70","author":"dauphin","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref23","article-title":"Location-relative attention mechanisms for robust long-form speech synthesis","author":"battenberg","year":"2019"}],"event":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Hong Kong","start":{"date-parts":[[2021,1,24]]},"end":{"date-parts":[[2021,1,27]]}},"container-title":["2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9362048\/9362049\/09362104.pdf?arnumber=9362104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:41:56Z","timestamp":1652182916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9362104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iscslp49672.2021.9362104","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}