{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:15:14Z","timestamp":1771964114576,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683519","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"7055-7059","source":"Crossref","is-referenced-by-count":16,"title":["Unsupervised Polyglot Text-to-speech"],"prefix":"10.1109","author":[{"given":"Eliya","family":"Nachmani","sequence":"first","affiliation":[]},{"given":"Lior","family":"Wolf","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Fitting new speakers based on a short un-transcribed sample","author":"nachmani","year":"2018","journal-title":"ICML"},{"key":"ref11","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018"},{"key":"ref12","article-title":"Voice imitating TTS neural networks","author":"lee","year":"2018"},{"key":"ref13","article-title":"Transfer learning from speaker verification to multispeaker TTS synthesis","author":"jia","year":"2018","journal-title":"NIPS"},{"key":"ref14","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"ICLR Workshop"},{"key":"ref15","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"NIPS"},{"key":"ref16","article-title":"Convolutional Sequence to Sequence Learning","author":"gehring","year":"2017","journal-title":"ICML"},{"key":"ref17","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref19","article-title":"Multilingual TTS synthesis","author":"black","year":"2004","journal-title":"ICASSP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-009-9109-9"},{"key":"ref4","article-title":"Deep voice: Real-time neural TTS","author":"arik","year":"2017","journal-title":"ICML"},{"key":"ref27","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017"},{"key":"ref3","article-title":"Clarinet: Parallel wave generation in end-to-end TTS","author":"ping","year":"2018"},{"key":"ref6","article-title":"Deep voice 3: 2000-speaker neural TTS","author":"ping","year":"2018","journal-title":"ICLRE"},{"key":"ref29","article-title":"Bavarian archive for speech signals (bas)","year":"2017"},{"key":"ref5","article-title":"Deep voice 2: Multi-speaker neural TTS","author":"arik","year":"2017","journal-title":"NIPS"},{"key":"ref8","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"ICASPP"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: A fully end-to-end TTS synthesis model","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref2","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"ICML"},{"key":"ref9","article-title":"VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop","author":"taigman","year":"2018","journal-title":"ICLRE"},{"key":"ref1","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref20","article-title":"From multilingual to polyglot speech synthesis","author":"traber","year":"1999","journal-title":"Sixth European Conference on Speech Communication and Technology"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2010.5656849"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CHINSL.2008.ECP.14"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2017.8300579"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495196"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472737"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683519.pdf?arnumber=8683519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:16:09Z","timestamp":1657854969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683519\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683519","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}