{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:13Z","timestamp":1774419373876,"version":"3.50.1"},"reference-count":39,"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\/icassp49660.2025.10889740","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens"],"prefix":"10.1109","author":[{"given":"Jinzheng","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Surrey,UK"}]},{"given":"Niko","family":"Moritz","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Egor","family":"Lakomkin","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Ruiming","family":"Xie","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Zhiping","family":"Xiu","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Katerina","family":"Zmolikova","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Zeeshan","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Duc","family":"Le","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Christian","family":"Fuegen","sequence":"additional","affiliation":[{"name":"Meta AI"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860774"},{"key":"ref2","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref5","article-title":"Cvss corpus and massively multilingual speech-to-speech translation","author":"Jia","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.58"},{"key":"ref7","article-title":"Seamlessm4t-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref9","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","first-page":"12449","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"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref13","article-title":"Speechtokenizer: Unified speech tokenizer for speech language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang"},{"key":"ref14","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref15","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref18","article-title":"Polyvoice: Language models for speech to speech translation","author":"Dong","year":"2023"},{"key":"ref19","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref20","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref21","article-title":"Transpeech: Speech-to-speech translation with bilateral perturbation","author":"Huang","year":"2022"},{"key":"ref22","article-title":"Transvip: Speech to speech translation system with voice and isochrony preservation","author":"Le","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096797"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.485"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.4"},{"key":"ref28","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref30","first-page":"10120","article-title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.872"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref35","article-title":"Sonar: sentence-level multimodal and language-agnostic representations","author":"Duquenne","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414560"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"}],"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\/10889740.pdf?arnumber=10889740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:33Z","timestamp":1774416153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889740","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}