{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:11:11Z","timestamp":1779379871557,"version":"3.53.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096797","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":20,"title":["Textless Direct Speech-to-Speech Translation with Discrete Speech Representation"],"prefix":"10.1109","author":[{"given":"Xinjian","family":"Li","sequence":"first","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Jia","sequence":"additional","affiliation":[{"name":"Tomato AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WINTECHCON55229.2022.9832314"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17684"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003853"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref30","article-title":"Lingvo: A modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10938"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383496"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref2","article-title":"CVSS corpus and massively multilingual speech-to-speech translation","author":"jia","year":"2022","journal-title":"Proc LREC"},{"key":"ref1","article-title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","author":"jia","year":"2022","journal-title":"Proc ICML"},{"key":"ref17","article-title":"Direct simultaneous speech to speech translation","author":"ma","year":"2021","journal-title":"ArXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref19","article-title":"TranSpeech: Speech-to-speech translation with bilateral perturbation","author":"huang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref23","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref26","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","author":"chiu","year":"2022","journal-title":"Proc ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11032"},{"key":"ref22","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref21","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref28","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc ICLR"},{"key":"ref27","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"bapna","year":"2022"},{"key":"ref29","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of International Conference on Artificial Intelligence and Statistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.166"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10712"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"ref4","first-page":"98","article-title":"Findings of the iwslt 2022 evaluation campaign","author":"antonios","year":"2022","journal-title":"Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)"},{"key":"ref3","article-title":"Improved speech-to-text translation with the Fisher and Callhome Spanish– English speech translation corpus","author":"post","year":"2013","journal-title":"Proc IWSLT"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195136241.001.0001","author":"nettle","year":"2000","journal-title":"Vanishing Voices The Extinction of the World's Languages"},{"key":"ref5","author":"schultz","year":"2006","journal-title":"Multilingual Speech Processing"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096797.pdf?arnumber=10096797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T06:13:43Z","timestamp":1702361623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096797","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}