{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:46:42Z","timestamp":1764398802825,"version":"3.46.0"},"reference-count":23,"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\/apsipaasc65261.2025.11249141","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"573-578","source":"Crossref","is-referenced-by-count":0,"title":["Conversation Context-Aware Direct Preference Optimization for Style-Controlled Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Atsushi","family":"Kojima","sequence":"first","affiliation":[{"name":"SB Intuitions,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[{"name":"SB Intuitions,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Shi","sequence":"additional","affiliation":[{"name":"SB Intuitions,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoya","family":"Mizumoto","sequence":"additional","affiliation":[{"name":"SB Intuitions,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengjie","family":"Zhao","sequence":"additional","affiliation":[{"name":"SB Intuitions,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yui","family":"Sudo","sequence":"additional","affiliation":[{"name":"SB Intuitions,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1098"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1995-292"},{"key":"ref4","article-title":"Conversational End-toEnd TTS for Voice Agent","volume-title":"Proc. SLT","author":"Guo","year":"2021"},{"key":"ref5","article-title":"Emotional End-to-End Neural Speech Synthesizer","author":"Lee","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-398"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446506"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1180"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1250\/ast.40.406"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref12","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. NeurIPS","author":"Rafailov","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref14","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume-title":"Proc. NeurIPS","author":"Kong","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888737"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3360885"},{"key":"ref21","article-title":"JSUT corpus: free largescale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.02.074"}],"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\/11249141.pdf?arnumber=11249141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:45:07Z","timestamp":1764398707000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249141","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}