{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:52Z","timestamp":1775229952479,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053255","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7774-7778","source":"Crossref","is-referenced-by-count":25,"title":["Emotional Voice Conversion Using Multitask Learning with Text-To-Speech"],"prefix":"10.1109","author":[{"given":"Tae-Ho","family":"Kim","sequence":"first","affiliation":[{"name":"KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea"}]},{"given":"Sungjae","family":"Cho","sequence":"additional","affiliation":[{"name":"Information and Electronics Research Institute,KAIST,Daejeon,Republic of Korea"}]},{"given":"Shinkook","family":"Choi","sequence":"additional","affiliation":[{"name":"Information and Electronics Research Institute,KAIST,Daejeon,Republic of Korea"}]},{"given":"Sejik","family":"Park","sequence":"additional","affiliation":[{"name":"KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea"}]},{"given":"Soo-Young","family":"Lee","sequence":"additional","affiliation":[{"name":"KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Close to human quality tts with transformer","author":"li","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-017-0116-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2923951"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.06.006"},{"key":"ref14","article-title":"Many-to-many voice conversion with out-of-dataset speaker support","author":"keskin","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref16","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018"},{"key":"ref17","article-title":"Emotional end-to-end neural speech synthesizer","author":"lee","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00031-6"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2004-576","article-title":"Pronunciation lexicon modeling and design for korean large vocabulary continuous speech recognition","author":"lee","year":"2004","journal-title":"Interspeech 2004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref8","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1703 10593"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682380"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.13064\/KSSS.2018.10.4.111"},{"key":"ref21","article-title":"Konlpy: Korean natural language processing in python","author":"park","year":"2014","journal-title":"Proc of the 26th Annual Conference on Human and Cognitive Language Technology"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053255.pdf?arnumber=9053255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:29:08Z","timestamp":1696015748000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053255","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}