{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:48Z","timestamp":1776888408366,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446214","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11931-11935","source":"Crossref","is-referenced-by-count":8,"title":["Speak While You Think: Streaming Speech Synthesis During Text Generation"],"prefix":"10.1109","author":[{"given":"Avihu","family":"Dekel","sequence":"first","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Slava","family":"Shechtman","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raul","family":"Fernandez","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Haws","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zvi","family":"Kons","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron","family":"Hoory","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ChatGPT","year":"2021"},{"key":"ref2","article-title":"Bard","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref4","article-title":"AudioGen: Textually Guided Audio Generation","volume-title":"ICLR","author":"Kreuk"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","article-title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","author":"Wang","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-40"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11066"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-546"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-538"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.346"},{"key":"ref13","first-page":"6621","article-title":"Speech-T: Transducer for Text to Speech and Beyond","volume-title":"Proc. NeurIPS","volume":"34","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1655"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2464"},{"key":"ref16","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"NeurIPS","volume":"35","author":"Ouyang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1032"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2442"},{"issue":"140","key":"ref20","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"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383591"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-388"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","article-title":"Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling","author":"Shen","year":"2020","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref28","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446214.pdf?arnumber=10446214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:06:19Z","timestamp":1722575179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446214","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}