{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T20:02:37Z","timestamp":1770753757342,"version":"3.50.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"MEXT KAKENHI","award":["16H06302"],"award-info":[{"award-number":["16H06302"]}]},{"name":"MEXT KAKENHI","award":["17H04687"],"award-info":[{"award-number":["17H04687"]}]},{"name":"MEXT KAKENHI","award":["18H04120"],"award-info":[{"award-number":["18H04120"]}]},{"name":"MEXT KAKENHI","award":["18H04112"],"award-info":[{"award-number":["18H04112"]}]},{"name":"MEXT KAKENHI","award":["18KT0051"],"award-info":[{"award-number":["18KT0051"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2872060","type":"journal-article","created":{"date-parts":[[2018,9,24]],"date-time":"2018-09-24T21:29:35Z","timestamp":1537824575000},"page":"60478-60488","source":"Crossref","is-referenced-by-count":47,"title":["Wasserstein GAN and Waveform Loss-Based Acoustic Model Training for Multi-Speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3555-9408","authenticated-orcid":false,"given":"Yi","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Shinji","family":"Takaki","sequence":"additional","affiliation":[]},{"given":"Hieu-Thi","family":"Luong","sequence":"additional","affiliation":[]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[]},{"given":"Daisuke","family":"Saito","sequence":"additional","affiliation":[]},{"given":"Nobuaki","family":"Minematsu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","author":"arik","year":"2017","journal-title":"Deep Voice Real-time neural text-to-speech"},{"key":"ref32","author":"lei","year":"2017","journal-title":"Training RNNs as fast as CNNs"},{"key":"ref31","author":"salimans","year":"2017","journal-title":"Pixelcnn++ Improving the pixelcnn with discretized logistic mixture likelihood and other modifications"},{"key":"ref30","first-page":"5769","article-title":"Improved training of wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref36","author":"le paine","year":"2016","journal-title":"Fast WaveNet generation algorithm"},{"key":"ref35","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"van den oord","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","author":"arjovsky","year":"2017","journal-title":"Wasserstein GAN"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref11","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","author":"van den oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref13","author":"van den oord","year":"2017","journal-title":"Parallel WaveNet Fast High-Fidelity Speech Synthesis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref15","author":"shen","year":"2017","journal-title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178817"},{"key":"ref19","first-page":"879","article-title":"A study of speaker adaptation for DNN-based speech synthesis","author":"wu","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref28","author":"wang","year":"2018","journal-title":"Style tokens Unsupervised style modeling control and transfer in end-to-end speech synthesis"},{"key":"ref4","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref27","first-page":"1","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283471"},{"key":"ref29","author":"mirza","year":"2014","journal-title":"Conditional generative adversarial nets"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1647"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178768"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953088"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-589"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-506"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"},{"key":"ref26","first-page":"1","article-title":"VoiceLoop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc 5th ISCA Workshop Speech Synthesis"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08471179.pdf?arnumber=8471179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:14:50Z","timestamp":1642004090000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8471179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2872060","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}