@inproceedings{fd296e73b2a145f2a1423e303fa55b00,
title = "SimulTron: On-Device Simultaneous Speech to Speech Translation",
abstract = "Simultaneous speech-to-speech translation (S2ST) holds the promise of breaking down communication barriers and enabling fluid conversations across languages. However, achieving accurate, real-time translation through mobile devices remains a major challenge. We introduce SimulTron, a novel S2ST architecture designed to tackle this task. SimulTron is a lightweight direct S2ST model that uses the strengths of the Translatotron framework while incorporating key modifications for streaming operation, and an adjustable fixed delay. Our experiments show that SimulTron surpasses Translatotron 2 in offline evaluations. Furthermore, real-time evaluations reveal that SimulTron improves upon the performance achieved by Translatotron 1. Additionally, SimulTron achieves superior BLEU scores and latency compared to previous real-time S2ST method on the MuST-C dataset. Significantly, we have successfully deployed SimulTron on a Pixel 7 Pro device, show its potential for simultaneous S2ST on-device.",
keywords = "On-device, Realtime, Speech to speech translation, Translatotron",
author = "Alex Agranovich and Eliya Nachmani and Oleg Rybakov and Yifan Ding and Ye Jia and Nadav Bar and Heiga Zen and Ramanovich, {Michelle Tadmor}",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 ; Conference date: 06-04-2025 Through 11-04-2025",
year = "2025",
month = jan,
day = "1",
doi = "10.1109/ICASSP49660.2025.10889296",
language = "American English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
editor = "Rao, {Bhaskar D} and Isabel Trancoso and Gaurav Sharma and Mehta, {Neelesh B.}",
booktitle = "2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 - Proceedings",
}