{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:41:55Z","timestamp":1725756115894},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639659","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"610-617","source":"Crossref","is-referenced-by-count":6,"title":["Scaling and Bias Codes for Modeling Speaker-Adaptive DNN-Based Speech Synthesis Systems"],"prefix":"10.1109","author":[{"given":"Hieu-Thi","family":"Luong","sequence":"first","affiliation":[]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.11.002"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1210"},{"journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit","year":"2017","author":"veaux","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854828"},{"key":"ref30","first-page":"2365","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition","author":"xue","year":"2013","journal-title":"InterSpeech"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref36","first-page":"712","article-title":"An investigation of multi-speaker training for wavenet vocoder","author":"hayashi","year":"2017","journal-title":"Proc ASRU"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1791"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1438"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref11","first-page":"705","article-title":"Integrated speaker-adaptive speech synthesis","author":"wan","year":"2017","journal-title":"Proc ASRU"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462178"},{"article-title":"Fitting new speakers based on a short untranscribed sample","year":"2018","author":"nachmani","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178817"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462373"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDP7165"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-460","article-title":"Embedding-based speaker adaptive training of deep neural networks","author":"cui","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.002"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.06.003"},{"article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","year":"2018","author":"wang","key":"ref3"},{"article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","year":"2018","author":"jia","key":"ref6"},{"key":"ref29","first-page":"774","article-title":"Learning factorized transforms for unsupervised adaptation of LSTM-RNN acoustic models","author":"samarakoon","year":"2017","journal-title":"Proc Interpeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282231"},{"key":"ref8","first-page":"879","article-title":"A study of speaker adaptation for DNN-based speech synthesis","author":"wu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461888"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2601146"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953116"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3404","DOI":"10.21437\/Interspeech.2017-1038","article-title":"Speaker adaptation in DNN-based speech synthesis using d-vectors","author":"doddipatla","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1131"},{"article-title":"Neural voice cloning with a few samples","year":"2018","author":"arik","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00061-2"},{"article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","year":"2018","author":"skerry-ryan","key":"ref25"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639659.pdf?arnumber=8639659","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T06:54:44Z","timestamp":1643266484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639659\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639659","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}