{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:50:40Z","timestamp":1783615840395,"version":"3.55.0"},"reference-count":42,"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\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","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\/icassp49660.2025.10888978","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models"],"prefix":"10.1109","author":[{"given":"Xin","family":"Jing","sequence":"first","affiliation":[{"name":"Technical University of Munich,CHI – Chair of Health Informatics,Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Triantafyllopoulos","sequence":"additional","affiliation":[{"name":"Technical University of Munich,CHI – Chair of Health Informatics,Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Technical University of Munich,CHI – Chair of Health Informatics,Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Expressivity and speech synthesis","author":"Triantafyllopoulos","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0089"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445996"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3250266"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-28"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3175578"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.508"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-754"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095515"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383526"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445996"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/9781394200801.ch31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3238007"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1779"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1337"},{"key":"ref19","article-title":"Text-to-image diffusion models in generative ai: A survey","author":"Zhang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref21","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Huang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref23","article-title":"Prompttts 2: Describing and generating voices with text prompt","author":"Leng","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1315"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639325"},{"key":"ref27","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Kim"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref29","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of International conference on machine learning (ICML)","author":"Radford"},{"key":"ref31","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref32","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proceedings of The International Conference on Learning Representations (ICLR)","author":"Song"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-12616-5_4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096760"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.30420\/456164010"},{"key":"ref37","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proceedings of The International Conference on Learning Representations (ICLR)","author":"Song"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"}],"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\/10888978.pdf?arnumber=10888978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:37Z","timestamp":1774416337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888978","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}