{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:10Z","timestamp":1774420150914,"version":"3.50.1"},"reference-count":4,"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\/icassp49660.2025.10890527","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-2","source":"Crossref","is-referenced-by-count":0,"title":["Discrete Unit-based Low-latency Multi-lingual Speech Synthesis for LIMMITS\u201925 Challenge"],"prefix":"10.1109","author":[{"given":"Yu","family":"Jiang","sequence":"first","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Gong","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Qiang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shenzhen Institute of Advanced Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3451951"},{"key":"ref2","article-title":"Ham-tts: Hierarchical acoustic modeling for token-based zero-shot text-to-speech with model and data scaling","author":"Wang","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3564118"},{"key":"ref4","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"}],"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\/10890527.pdf?arnumber=10890527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:40Z","timestamp":1774416400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":4,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890527","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}