{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:00:33Z","timestamp":1764403233396,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10037859","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"86-90","source":"Crossref","is-referenced-by-count":3,"title":["HILvoice:Human-in-the-Loop Style Selection for Elder-Facing Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Xueyuan","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Qiaochu","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288797"},{"article-title":"Emotional end-to-end neural speech synthesizer","volume-title":"NeurIPS","author":"Lee","key":"ref3"},{"key":"ref4","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International Conference on Machine Learning","author":"Wang"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3052688"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1129"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"key":"ref10","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume-title":"Advances in neural information processing systems","volume":"30","author":"Hsu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747747"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11345"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WSS.2002.1224408"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA50338.2020.9295000"},{"key":"ref15","first-page":"3685","article-title":"GFM-Voc: A real-time voice quality modification system","volume-title":"Interspeech 2019-20th Annual Conference of the International Speech Communication Association","author":"Perrotin"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-257"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273556"},{"issue":"2","key":"ref18","article-title":"Random search for hyper-parameter optimization","volume-title":"Journal of machine learning research","volume":"13","author":"Bergstra"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-90328-2_16"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10037859.pdf?arnumber=10037859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:57:14Z","timestamp":1707832634000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10037859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10037859","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}