{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:46Z","timestamp":1774419406227,"version":"3.50.1"},"reference-count":36,"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\/icassp49660.2025.10889296","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["SimulTron: On-Device Simultaneous Speech to Speech Translation"],"prefix":"10.1109","author":[{"given":"Alex","family":"Agranovich","sequence":"first","affiliation":[{"name":"Google Research"}]},{"given":"Eliya","family":"Nachmani","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Oleg","family":"Rybakov","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Yifan","family":"Ding","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Ye","family":"Jia","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Nadav","family":"Bar","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Michelle Tadmor","family":"Ramanovich","sequence":"additional","affiliation":[{"name":"Google Research"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17684"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref5","article-title":"TranSpeech: Speech-to-speech translation with bilateral perturbation","author":"Huang","year":"2022"},{"key":"ref6","article-title":"Simultaneous speech-to-speech translation system with neural incremental asr, mt, and tts","author":"Sudoh","year":"2020"},{"key":"ref7","article-title":"Direct simultaneous speech-to-speech translation with variational monotonic multihead attention","author":"Ma","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10568"},{"key":"ref9","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023"},{"key":"ref10","article-title":"Learning when to speak: Latency and quality tradeoffs for simultaneous speech-to-speech translation with offline models","author":"Dugan","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860774"},{"key":"ref12","volume-title":"Verbmobil: Foundations of speech-to-speech translation","author":"Wahlster","year":"2013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599557"},{"key":"ref14","first-page":"10120","article-title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448426"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.602"},{"key":"ref17","article-title":"Improving cascaded unsupervised speech translation with denoising back-translation","author":"Fu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003853"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in neural information processing systems","volume":"33","author":"Baevski"},{"key":"ref21","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095616"},{"key":"ref25","article-title":"Many-to-many spoken language translation via unified speech and text representation learning with unit-to-unit translation","author":"Kim","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.872"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096797"},{"key":"ref28","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref29","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"Shen","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1289"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-160"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1137"},{"key":"ref33","article-title":"TensorFlow Lite \u2014 ML for Mobile and Edge Devices \u2014 tensorflow.org"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"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\/10889296.pdf?arnumber=10889296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:43Z","timestamp":1774416163000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889296","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}