{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:28Z","timestamp":1774419628930,"version":"3.50.1"},"reference-count":2,"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\/icassp49660.2025.10890358","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-2","source":"Crossref","is-referenced-by-count":0,"title":["Build LLM-Based Zero-Shot Streaming TTS System with Cosyvoice"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Lyu","sequence":"first","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huadai","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Du","sequence":"additional","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens[J]","author":"Du","year":"2024"},{"key":"ref2","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision[C]","volume-title":"International conference on machine learning","author":"Radford"}],"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\/10890358.pdf?arnumber=10890358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:50Z","timestamp":1774416230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":2,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890358","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}