{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:24Z","timestamp":1764399084560,"version":"3.46.0"},"reference-count":31,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2053,62176182"],"award-info":[{"award-number":["U23B2053,62176182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249104","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"555-560","source":"Crossref","is-referenced-by-count":0,"title":["Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS"],"prefix":"10.1109","author":[{"given":"Haoyu","family":"Wang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Qiang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Gong","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, China Telecom,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref1"},{"key":"ref2","article-title":"Seed-TTS: A family of high-quality versatile speech generation models","author":"Anastassiou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3434425"},{"key":"ref5","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447797"},{"key":"ref8","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref9","first-page":"22 199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Proc. NIPS"},{"issue":"70","key":"ref10","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00205"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.811"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26563"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1337"},{"key":"ref17","article-title":"Mm-tts: A unified framework for multimodal, prompt-induced emotional text-to-speech synthesis","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3451951"},{"key":"ref19","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2010.02.002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2009578"},{"issue":"1","key":"ref22","first-page":"19","article-title":"Pitch in emotional speech and emotional speech recognition using pitch frequency","volume":"4","author":"Gharavian","year":"2010","journal-title":"Majlesi Journal of Electrical Engineering"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-2909.97.3.412"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095840"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref30","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for taskagnostic compression of pre-trained transformers","volume":"33","author":"Wang","year":"2020","journal-title":"Proc. NIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-9996"}],"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\/11249104.pdf?arnumber=11249104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:23Z","timestamp":1764399023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249104","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}