{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:19Z","timestamp":1774419799959,"version":"3.50.1"},"reference-count":30,"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\/icassp49660.2025.10890055","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Zehai","family":"Tu","sequence":"first","affiliation":[{"name":"LightSpeed Studios, Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"LightSpeed Studios, Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiting","family":"Lu","sequence":"additional","affiliation":[{"name":"LightSpeed Studios, Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adaeze","family":"Adigwe","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwen","family":"Guo","sequence":"additional","affiliation":[{"name":"LightSpeed Studios, Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref4","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref6","article-title":"The curious case of neural text degeneration","volume-title":"International Conference on Learning Representations","author":"Holtzman"},{"key":"ref7","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref9","article-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","author":"Lyth","year":"2024"},{"key":"ref10","article-title":"Seed-tts: A family of high-quality versatile speech generation models","author":"Anastassiou","year":"2024"},{"key":"ref11","article-title":"Base tts: Lessons from building a billionparameter text-to-speech model on 100k hours of data","author":"Lajszczak","year":"2024"},{"key":"ref12","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"issue":"8","key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref17","article-title":"A simple, fast diverse decoding algorithm for neural generation","author":"Li","year":"2016"},{"key":"ref18","article-title":"Diverse beam search: Decoding diverse solutions from neural sequence models","author":"Vijayakumar","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-8609"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3530270"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref25","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414423"},{"key":"ref27","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1513"}],"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\/10890055.pdf?arnumber=10890055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:46Z","timestamp":1774416286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890055","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}