{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:05Z","timestamp":1775230025635,"version":"3.50.1"},"reference-count":20,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414043","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7078-7082","source":"Crossref","is-referenced-by-count":10,"title":["Litesing: Towards Fast, Lightweight and Expressive Singing Voice Synthesis"],"prefix":"10.1109","author":[{"given":"Xiaobin","family":"Zhuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Szu-Yu","family":"Chou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Lui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Singing voice synthesis based on convolutional neural networks","author":"nakamura","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903099"},{"key":"ref12","article-title":"Wasserstein gan","author":"arjovsky","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref14","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019"},{"key":"ref15","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref16","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref18","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018"},{"key":"ref19","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019"},{"key":"ref4","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref6","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019"},{"key":"ref5","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018"},{"key":"ref8","article-title":"Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens","author":"valle","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1420"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.323266"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-872"},{"key":"ref9","article-title":"Durian: Duration informed attention network for multimodal synthesis","author":"yu","year":"2019"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2017"}],"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\/09414043.pdf?arnumber=9414043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:57Z","timestamp":1652197257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414043","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}