{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:55:59Z","timestamp":1774162559682,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"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\/icassp39728.2021.9414872","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"6613-6617","source":"Crossref","is-referenced-by-count":35,"title":["Adaspeech 2: Adaptive Text to Speech with Untranscribed Data"],"prefix":"10.1109","author":[{"given":"Yuzi","family":"Yan","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohan","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Azure Speech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Azure Speech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Shen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3034994"},{"key":"ref12","article-title":"Voiceloop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"2017"},{"key":"ref13","author":"luong","year":"2019"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref17","article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"veaux","year":"2016"},{"key":"ref18","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1208"},{"key":"ref4","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"NIPS"},{"key":"ref3","first-page":"10019","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"NIPS"},{"key":"ref6","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"li","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref8","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"chen","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref7","first-page":"4879","article-title":"Generalized end-to-end loss for speaker verification","author":"wan","year":"2018","journal-title":"ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref1","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2018"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref20","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1043"}],"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\/09414872.pdf?arnumber=9414872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:37:20Z","timestamp":1767033440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414872","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}