{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T08:23:19Z","timestamp":1771489399231,"version":"3.50.1"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"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":[[2025,11,12]]},"DOI":"10.1109\/o-cocosda68185.2025.11385230","type":"proceedings-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:14:09Z","timestamp":1771449249000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Toward Natural Emotional Text-to-Speech System with Fine-Grained Non-Verbal Expression Control"],"prefix":"10.1109","author":[{"given":"Wangzixi","family":"Zhou","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology,Ikoma,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bagus Tris","family":"Atmaja","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Ikoma,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Ikoma,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9781351308724"},{"key":"ref2","first-page":"196","article-title":"Affect bursts","volume":"161","author":"Klaus","year":"1994","journal-title":"Emotions: Essays on emotion theory"},{"key":"ref3","first-page":"1","article-title":"The ami meeting corpus","volume-title":"Proc. International Conference on Methods and Techniques in Behavioral Research","author":"Kraaij"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2025-16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1905"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.103004"},{"key":"ref8","article-title":"Cosyvoice 2: Scalable streaming speech synthesis with large language models","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-153"},{"key":"ref10","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford"},{"key":"ref11","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International conference on machine learning. PMLR","author":"Popov"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2010.5583006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref16","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"Proc. NeurIPS"}],"event":{"name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Yogyakarta, Indonesia","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,14]]}},"container-title":["2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11383559\/11384821\/11385230.pdf?arnumber=11385230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T07:30:07Z","timestamp":1771486207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11385230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda68185.2025.11385230","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}