{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:01:24Z","timestamp":1764399684672,"version":"3.46.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249123","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"795-800","source":"Crossref","is-referenced-by-count":0,"title":["EFTTS: Zero-Shot Emotional Speech Synthesis via Conditional Flow Matching and Self-Supervised Representations"],"prefix":"10.1109","author":[{"given":"Haoyu","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiale","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxun","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sizhe","family":"Shan","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuehai","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747098"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3395994"},{"key":"ref8","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","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413907"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446467"},{"key":"ref12","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445948"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1317"},{"key":"ref17","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Styletts 2: Towards human-level text-tospeech through style diffusion and adversarial training with large speech language models","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10097074"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref22","article-title":"Bigvgan: A universal neural vocoder with largescale training","author":"Lee","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Emotion2vec: Selfsupervised pre-training for speech emotion representation","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref27","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"volume-title":"Mel cepstral distortion (mcd) computations in python","year":"2021","author":"Shannon","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-398"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249123.pdf?arnumber=11249123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:57:43Z","timestamp":1764399463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249123","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}