{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:28Z","timestamp":1775230108022,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097118","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Fine-Grained Emotional Control of Text-to-Speech: Learning to Rank Inter- and Intra-Class Emotion Intensities"],"prefix":"10.1109","author":[{"given":"Shijun","family":"Wang","sequence":"first","affiliation":[{"name":"University of St.Gallen,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00f3n","family":"Gu\u00f0nason","sequence":"additional","affiliation":[{"name":"Reykjavik University,Iceland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Damian","family":"Borth","sequence":"additional","affiliation":[{"name":"University of St.Gallen,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Controllability and interpretability in affective speech synthesis","author":"schnell","year":"2022","journal-title":"Tech Rep"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892405"},{"key":"ref14","article-title":"mixup: Beyond empirical risk minimization","volume":"abs 1710 9412","author":"zhang","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"ICLRE"},{"key":"ref17","article-title":"The emotional voices database: Towards controlling the emotion dimension in voice generation systems","volume":"abs 1806 9514","author":"adigwe","year":"2018"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-307"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref8","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"ICML"},{"key":"ref7","article-title":"Expressive neural voice cloning","volume":"abs 2102 151","author":"neekhara","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref4","volume":"abs 2006 4558","author":"ren","year":"2021","journal-title":"Fastspeech 2 Fast and high-quality end-to-end text to speech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-831"},{"key":"ref6","article-title":"Emotional end-to-end neural speech synthesizer","volume":"abs 1711 5447","author":"lee","year":"2017"},{"key":"ref5","volume":"abs 2106 15561","author":"tan","year":"2021","journal-title":"A survey on neural speech synthesis"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097118.pdf?arnumber=10097118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:24Z","timestamp":1700507304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097118","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}