{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:04:39Z","timestamp":1776888279153,"version":"3.51.2"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"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":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428161","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T21:14:21Z","timestamp":1623273261000},"page":"1-6","source":"Crossref","is-referenced-by-count":29,"title":["Fastsvc: Fast Cross-Domain Singing Voice Conversion With Feature-Wise Linear Modulation"],"prefix":"10.1109","author":[{"given":"Songxiang","family":"Liu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Human-Computer Communications Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuewen","family":"Cao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Human-Computer Communications Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Human-Computer Communications Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref30","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"yamagishi","year":"2019"},{"key":"ref10","article-title":"Vaw-gan for singing voice conversion with non-parallel training data","author":"lu","year":"2020"},{"key":"ref11","article-title":"Ppg-based singing voice conversion with adversarial representation learning","author":"li","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1862"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref17","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"2017"},{"key":"ref18","first-page":"5206","article-title":"Lib-rispeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1043"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683154"},{"key":"ref27","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-580"},{"key":"ref6","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"ISCA SSW6"},{"key":"ref29","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023162"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1761"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-539"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054582"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367303"},{"key":"ref20","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"NeurIPS"},{"key":"ref22","first-page":"524","article-title":"Fast and flexible neural audio synthesis","author":"hantrakul","year":"2019","journal-title":"ISMIR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref24","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016"},{"key":"ref23","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"chen","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,5]]},"end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428161.pdf?arnumber=9428161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T21:27:58Z","timestamp":1656365278000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428161","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}