{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:20:23Z","timestamp":1753600823334,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383585","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T16:46:54Z","timestamp":1616690814000},"page":"522-529","source":"Crossref","is-referenced-by-count":3,"title":["Learn2Sing: Target Speaker Singing Voice Synthesis by Learning from a Singing Teacher"],"prefix":"10.1109","author":[{"given":"Heyang","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiulin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682656"},{"key":"ref11","article-title":"Durian-sc: Duration informed attention network based singing voice conversion system","volume":"2020","author":"zhang","year":"2020","journal-title":"InterSpeech"},{"article-title":"Durian: Duration informed attention network for multimodal synthesis","year":"2019","author":"yu","key":"ref12"},{"year":"2019","author":"valle","key":"ref13"},{"key":"ref14","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018 Stockholmsmässan Stockholm Sweden July 10-15 2018"},{"key":"ref15","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning ICML 2015"},{"key":"ref16","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref17","first-page":"1296","article-title":"Adversarially trained multi-singer sequence-to-sequence singing synthesizer","author":"wu","year":"2020","journal-title":"Interspeech 2020 21st Annual Conference of the International Speech Communication Association Virtual Event"},{"article-title":"Mixture density networks","year":"1994","author":"bishop","key":"ref18"},{"year":"2015","author":"talkin","key":"ref19"},{"key":"ref4","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018 Stockholmsmässan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472730"},{"article-title":"Singing voice synthesis based on convolutional neural networks","year":"2019","author":"nakamura","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1575"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"7962","DOI":"10.1109\/ICASSP.2013.6639215","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP 2013"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"article-title":"Bytesing: A chinese singing voice synthesis system using duration allocated encoder-decoder acoustic models and wavernn vocoders","year":"2020","author":"gu","key":"ref9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383585.pdf?arnumber=9383585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T20:21:41Z","timestamp":1698092501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383585","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}