{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:16:06Z","timestamp":1764400566562,"version":"3.46.0"},"reference-count":27,"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\/apsipaasc65261.2025.11249309","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"789-794","source":"Crossref","is-referenced-by-count":0,"title":["A Study of Japanese Mixed Emotional Speech Synthesis Based on an End-to-End Emotional Speech Synthesis Model"],"prefix":"10.1109","author":[{"given":"Issei","family":"Sakata","sequence":"first","affiliation":[{"name":"Graduate School of Science and Engineering, Yamagata University,Yonezawa,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuo","family":"Kosaka","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Engineering, Yamagata University,Yonezawa,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","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"},{"journal-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"},{"key":"ref6","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1317"},{"key":"ref8","article-title":"Daisy-TTS: Simulating wider spectrum of emotions via prosody embedding decomposition","author":"Chevi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"International conference on machine learning","author":"Rezende","year":"2015"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3360885"},{"issue":"Nov","key":"ref16","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"journal-title":"Vits-uma-genshin-honkai - a Hugging Face Space by zomehwh","year":"2025","key":"ref18"},{"key":"ref19","article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832315"},{"key":"ref21","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/blizzard.2008-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2009-1"},{"key":"ref25","article-title":"The Blizzard Challenge 2010","volume-title":"Proc. Blizzard Challenge Workshop","author":"Black","year":"2010"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2011-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10922"},{"journal-title":"sarulab-speech\/VMC2024-sarulab-data","year":"2025","key":"ref28"}],"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\/11249309.pdf?arnumber=11249309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:49Z","timestamp":1764400309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249309","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}