{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T04:47:23Z","timestamp":1746679643712,"version":"3.37.3"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3021758","type":"journal-article","created":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T21:01:40Z","timestamp":1599253300000},"page":"161713-161719","source":"Crossref","is-referenced-by-count":13,"title":["Effective Emotion Transplantation in an End-to-End Text-to-Speech System"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7428-5868","authenticated-orcid":false,"given":"Young-Sun","family":"Joo","sequence":"first","affiliation":[{"name":"Speech AI Lab., NCSOFT Corporation, Gyeonggi-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanbin","family":"Bae","sequence":"additional","affiliation":[{"name":"Speech AI Lab., NCSOFT Corporation, Gyeonggi-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young-Ik","family":"Kim","sequence":"additional","affiliation":[{"name":"Speech AI Lab., NCSOFT Corporation, Gyeonggi-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6850-6580","authenticated-orcid":false,"given":"Hoon-Young","family":"Cho","sequence":"additional","affiliation":[{"name":"Speech AI Lab., NCSOFT Corporation, Gyeonggi-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6554-0783","authenticated-orcid":false,"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Waveglow","year":"2018","author":"prenger","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref30","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref10","first-page":"1","article-title":"Emotional end-to-end neural speech synthesizer","author":"lee","year":"2017","journal-title":"Proc NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-171"},{"key":"ref12","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume":"80","author":"skerry-ryan","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref13","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref14","first-page":"318","article-title":"Learning internal representations by error propagation","volume":"1","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition"},{"key":"ref15","article-title":"Uncovering latent style factors for expressive speech synthesis","author":"wang","year":"2017","journal-title":"arXiv 1711 00520"},{"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","first-page":"879","article-title":"A study of speaker adaptation for DNN-based speech synthesis","author":"wu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820721"},{"key":"ref28","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2819886"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2746264"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref29","volume":"3","author":"duda","year":"1973","journal-title":"Pattern Classification and Scene Analysis"},{"key":"ref5","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref7","first-page":"1","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc ICLR"},{"key":"ref2","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2385478"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1038"},{"key":"ref22","first-page":"1","article-title":"Emotional transplant in statistical speech synthesis based on emotion additive model","author":"ohtani","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461888"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282231"},{"key":"ref26","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"80","author":"van den oord","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09186605.pdf?arnumber=9186605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:01:39Z","timestamp":1662667299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9186605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3021758","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}