{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T01:27:49Z","timestamp":1775698069581,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888737","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization"],"prefix":"10.1109","author":[{"given":"Xiaoxue","family":"Gao","sequence":"first","affiliation":[{"name":"Agency for Science, Technology, and Research (A*STAR),Institute for Infocomm Research (I2R),Singapore"}]},{"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Yiming","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Huayun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology, and Research (A*STAR),Institute for Infocomm Research (I2R),Singapore"}]},{"given":"Nancy F.","family":"Chen","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology, and Research (A*STAR),Institute for Infocomm Research (I2R),Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094298"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26488"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.12720\/jait.13.5.398-412"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.9.1406"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-17"},{"key":"ref7","article-title":"Emotional end-to-end neural speech synthesizer","author":"Lee","year":"2017"},{"key":"ref8","article-title":"Mm-tts: A unified framework for multimodal, prompt-induced emotional text-to-speech synthesis","author":"Li","year":"2024"},{"key":"ref9","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"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3443711"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3533357"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29833"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-465"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/app13042225"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832181"},{"key":"ref21","article-title":"Clam-tts: Improving neural codec language model for zero-shot text-to-speech","volume-title":"The Twelfth International Conference on Learning Representations","author":"Kim"},{"key":"ref22","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024"},{"key":"ref23","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref25","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref26","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Rafailov"},{"key":"ref27","article-title":"Towards a unified view of preference learning for large language models: A survey","author":"Gao","year":"2024"},{"key":"ref28","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref29","article-title":"Speechalign: Aligning speech generation to human preferences","author":"Zhang","year":"2024"},{"key":"ref30","article-title":"Musicrl: Aligning music generation to human preferences","author":"Cideron","year":"2024"},{"key":"ref31","article-title":"Boost your own human image generation model via direct preference optimization with ai feedback","author":"Na","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref33","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref34","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(96)00063-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref37","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023056"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"252","DOI":"10.21437\/Odyssey.2020-36","article-title":"Personalized singing voice generation using wavemn","author":"Gao","year":"2020","journal-title":"Odyssey"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888737.pdf?arnumber=10888737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:23Z","timestamp":1774416143000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888737","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}