{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:39:01Z","timestamp":1753601941052,"version":"3.37.3"},"reference-count":19,"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\/icassp39728.2021.9414400","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"8383-8387","source":"Crossref","is-referenced-by-count":10,"title":["Light-TTS: Lightweight Multi-Speaker Multi-Lingual Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Song","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beibei","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"NIPS 2018 The 32nd Annual Conference on Neural Information Processing Systems"},{"key":"ref11","first-page":"10019","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"NIPS 2018 The 32nd Annual Conference on Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"article-title":"Pay less attention with lightweight and dynamic convolutions","year":"2019","author":"wu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref18","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"article-title":"Close to human quality TTS with Transformer","year":"2018","author":"li","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Parallel neural text-to-speech","year":"2019","author":"peng","key":"ref6"},{"key":"ref5","first-page":"2205","article-title":"DurIAN: Duration informed attention network for multimodal synthesis","author":"yu","year":"2019","journal-title":"Interspeech 2019"},{"article-title":"Problem-agnostic speech embeddings for multispeaker text-to-speech with samplernn","year":"2019","author":"alvarez","key":"ref8"},{"key":"ref7","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0048-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","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\/09414400.pdf?arnumber=9414400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:50Z","timestamp":1652197250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414400","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}