{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:49:33Z","timestamp":1771519773488,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832181","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"690-697","source":"Crossref","is-referenced-by-count":6,"title":["Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-To-Speech"],"prefix":"10.1109","author":[{"given":"Haibin","family":"Wu","sequence":"first","affiliation":[{"name":"National Taiwan University"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Sefik Emre","family":"Eskimez","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Manthan","family":"Thakker","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Daniel","family":"Tompkins","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Chung-Hsien","family":"Tsai","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Canrun","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Zhen","family":"Xiao","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app13042225"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446467"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1317"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2022.3233324"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095623"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"853864","DOI":"10.1109\/TASLP.2022.3145293","article-title":"MsE-moTTS: Multi-scale emotion transfer, prediction, and control for emotional speech synthesis","volume":"30","author":"Lei","year":"2022","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10131"},{"key":"ref9","article-title":"Emotional end-to-end neural speech synthesizer","author":"Lee","year":"2017","journal-title":"arXiv preprint arXiv:1711.05447"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-398"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref14","article-title":"Making flow-matching-based zero-shot text-to-speech laugh as you like","author":"Kanda","year":"2024","journal-title":"arXiv preprint arXiv:2402.07383"},{"key":"ref15","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"ICLR 2023"},{"key":"ref16","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173932"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-353"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref21","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv preprint arXiv:2403.03100"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref23","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1336"},{"key":"ref25","article-title":"emotion2vec: Self-supervised pre-training for speech emotion representation","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv:2312.15185"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","first-page":"28","article-title":"The AMI meeting corpus: A pre-announcement","volume-title":"ICMI 2005.","author":"Carletta"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref31","first-page":"69","article-title":"The Fisher corpus: A resource for the next generations of speech-to-text","volume":"4","author":"Cieri","year":"2004","journal-title":"LREC"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3360885"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446050"},{"key":"ref35","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML 2023. PMLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref37","article-title":"Neural codec language models are zero-shot text-to-speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref38","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2312.05187"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"GPT-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1327"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832181.pdf?arnumber=10832181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T18:31:36Z","timestamp":1737138696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832181","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}