{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T17:07:24Z","timestamp":1790528844635,"version":"4.1.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413391","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"920-924","source":"Crossref","is-referenced-by-count":166,"title":["Seen and Unseen Emotional Style Transfer for Voice Conversion with A New Emotional Speech Dataset"],"prefix":"10.1109","author":[{"given":"Kun","family":"Zhou","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Berrak","family":"Sisman","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design,Information Systems Technology and Design"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design,Information Systems Technology and Design"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref32","article-title":"Expressive tts training with frame and style reconstruction loss","author":"liu","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref30","article-title":"Interactive text-to-speech via semi-supervised style transfer learning","author":"gao","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003939"},{"key":"ref11","article-title":"Prosody conversion from neutral speech to emotional speech","author":"tao","year":"2006","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041640"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2016.7550889"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1053"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683865"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.06.006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1325"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2878"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054681"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2910637"},{"key":"ref2","article-title":"Emotion and personality","author":"arnold","year":"1960"},{"key":"ref9","article-title":"High-order sequence modeling using speaker-dependent recurrent temporal restricted boltzmann machines for voice conversion","author":"nakashika","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref1","first-page":"515","article-title":"Pragmatics and intonation","author":"hirschberg","year":"2004","journal-title":"The Handbook of Pragmatics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-63","article-title":"Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks","author":"hsu","year":"2017"},{"key":"ref24","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref23","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref26","article-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","author":"latif","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/1754073919898526"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413391.pdf?arnumber=9413391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:40Z","timestamp":1659486040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413391","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}