{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:43:21Z","timestamp":1776883401246,"version":"3.51.2"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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"}]},{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848721","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["Fine-Grained Quantitative Emotion Editing for Speech Generation"],"prefix":"10.1109","author":[{"given":"Sho","family":"Inoue","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab, Institute for Intelligent Computing,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3250266"},{"key":"ref2","article-title":"Emotion modelling for speech generation","author":"KUN","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9780470756959.ch23"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref6","first-page":"79","article-title":"Emotion recognition using prosodic information","volume-title":"Emotion Recognition using Speech Features","author":"Krothapalli","year":"2013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383526"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10249"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-802"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10288-021-00473-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414633"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-26"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.20396\/joss.v1i1.15014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-558"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2010.02.002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/s0095-4470(19)30625-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1053"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11171"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10445996"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413907"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iscslp49672.2021.9362069"},{"key":"ref25","article-title":"Adjusting pleasure-arousal-dominance for continuous emotional text-to-speech synthesizer","volume-title":"Interspeech","author":"Rabiee","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/asru46091.2019.9003829"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2022.3175578"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2022.3233324"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383524"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10097118"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747098"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688051"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1386"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref38","article-title":"The blizzard challenge 2013","author":"King","year":"2014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref41","author":"Ren","year":"2022","journal-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech"},{"key":"ref42","author":"Vaswani","year":"2017","journal-title":"Attention is all you need"},{"key":"ref43","author":"Kingma","year":"2017","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref44","author":"Kong","year":"2020","journal-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/pacrim.1993.407206"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ialp.2017.8300542"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-2074"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Macau, Macao","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848721.pdf?arnumber=10848721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:08:14Z","timestamp":1738044494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848721","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}