{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:03:48Z","timestamp":1764403428568,"version":"3.32.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"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":[[2024,10,17]]},"DOI":"10.1109\/o-cocosda64382.2024.10800372","type":"proceedings-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T18:56:08Z","timestamp":1734720968000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Learning Contrastive Emotional Nuances in Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Bryan Gautama","family":"Ngo","sequence":"first","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahdin","family":"Rohmatillah","sequence":"additional","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Tzung","family":"Chien","sequence":"additional","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"670","article-title":"Promoting mental self-disclosure in a spoken dialogue system","volume-title":"Proc. of Annual Conference of International Speech Communication Association","volume":"2023","author":"Rohmatillah","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389638"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1212"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038221"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1148"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10761"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402077"},{"key":"ref15","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. of International Conference on Machine Learning","author":"Wang","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref17","article-title":"Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis","volume-title":"International Conference on Learning Representations","author":"Valle","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref19","first-page":"21","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","volume-title":"Proc. of International Conference on Machine Learning","volume":"117","author":"Jaitly","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1229"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432631"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1652"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3044215"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446746"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"}],"event":{"name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","start":{"date-parts":[[2024,10,17]]},"location":"Hsinchu City, Taiwan","end":{"date-parts":[[2024,10,19]]}},"container-title":["2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799946\/10799972\/10800372.pdf?arnumber=10800372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T06:18:57Z","timestamp":1734761937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda64382.2024.10800372","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]}}}