{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:52:10Z","timestamp":1774896730494,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210021","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["A Multi-Stage Framework for Multimodal Controllable Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Rui","family":"Niu","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihao","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent,Youtu Lab,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Ma","sequence":"additional","affiliation":[{"name":"Tencent,Youtu Lab,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Mega-tts 2: Boosting prompting mechanisms for zero-shot speech synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jiang"},{"key":"ref2","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024"},{"key":"ref3","article-title":"Maskgct: Zero-shot text-to-speech with masked generative codec transformer","author":"Wang","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448433"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2136"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448173"},{"key":"ref11","article-title":"Mm-tts: A unified framework for multimodal, prompt-induced emotional text-to-speech synthesis","author":"Li","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29769"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref15","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume":"35","author":"Bangalath","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475286"},{"key":"ref17","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref18","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":"ref19","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-692"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"issue":"140","key":"ref29","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210021.pdf?arnumber=11210021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:40:40Z","timestamp":1761889240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210021","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}