{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:24:08Z","timestamp":1774419848151,"version":"3.50.1"},"reference-count":41,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889012","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Li","sequence":"first","affiliation":[{"name":"Shenzhen Technology University"}]},{"given":"Zhi-Qi","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Jun-Yan","family":"He","sequence":"additional","affiliation":[{"name":"DAMO Academy,Alibaba Group"}]},{"given":"Junyao","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University"}]},{"given":"Xiaomao","family":"Fan","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University"}]},{"given":"Xiaojiang","family":"Peng","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University"}]},{"given":"Alexander G.","family":"Hauptmann","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1148"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-513"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref10","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref12","article-title":"Nice: Non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"ref13","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"},{"key":"ref14","first-page":"7700","article-title":"Efficienttts: An efficient and high-quality text-to-speech architecture","volume-title":"International Conference on Machine Learning","author":"Miao"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-17"},{"key":"ref16","article-title":"Emotional end-to-end neural speech synthesizer","author":"Lee","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref19","article-title":"Cross-speaker emotion transfer based on speaker condition layer normalization and semi-supervised training in text-to-speech","author":"Wu","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref22","first-page":"10970","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Huang","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3363444"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref25","article-title":"Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning","author":"Cheng","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689404"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29769"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref35","article-title":"Wavenet: A generative model for raw audio","volume":"12","author":"Van Den Oord","year":"2016"},{"key":"ref36","article-title":"Instructerc: Reforming emotion recognition in conversation with a retrieval multi-task llms framework","author":"Lei","year":"2023"},{"key":"ref37","first-page":"12 449","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":"ref38","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref39","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref40","article-title":"mel-cepstral-distance","author":"Sternkopf","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462665"}],"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\/10889012.pdf?arnumber=10889012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:01Z","timestamp":1774416301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889012","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}