{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:14:38Z","timestamp":1771611278752,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054535","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6184-6188","source":"Crossref","is-referenced-by-count":121,"title":["Zero-Shot Multi-Speaker Text-To-Speech with State-Of-The-Art Neural Speaker Embeddings"],"prefix":"10.1109","author":[{"given":"Erica","family":"Cooper","sequence":"first","affiliation":[]},{"given":"Cheng-I","family":"Lai","sequence":"additional","affiliation":[]},{"given":"Yusuke","family":"Yasuda","sequence":"additional","affiliation":[]},{"given":"Fuming","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Nanxin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"The blizzard challenge 2011","author":"king","year":"2011","journal-title":"Blizzard Challenge Workshop"},{"key":"ref38","year":"2005","journal-title":"Recommendation G 191 Software Tools and Audio Coding Standardization"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref32","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0"},{"key":"ref31","article-title":"Flite: a small fast run-time synthesis engine","author":"black","year":"2001","journal-title":"Proc 4th ISCA Tutorial and Research Workshop on Speech Synthesis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3146"},{"key":"ref37","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017","journal-title":"Centre for Speech Technology Research University of Edinburgh"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.001"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639151"},{"key":"ref34","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref10","article-title":"Modeling multi-speaker latent space to improve neural TTS: Quick enrolling new speaker and enhancing premium voice","author":"deng","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2830"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-5"},{"key":"ref12","first-page":"10 019","article-title":"Neural voice cloning with a few samples","author":"ar?k","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2713"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Odyssey.2018-11","article-title":"Exploring the encoding layer and loss function in end-to-end speaker and language recognition system","author":"cai","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref4","article-title":"Multi-speaker end-to-end speech synthesis","author":"park","year":"2019","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2019","journal-title":"ICLRE"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref8","article-title":"Multi-speaker end-to-end speech synthesis","author":"park","year":"4462"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1333"},{"key":"ref2","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2018","journal-title":"ICLRE"},{"key":"ref9","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"2018","journal-title":"ICML"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1782"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref23","article-title":"Unified hypersphere embedding for speaker recognition","author":"hajibabaei","year":"2018"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2177"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054535.pdf?arnumber=9054535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:24:04Z","timestamp":1656375844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054535","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}