SimulTron: On-Device Simultaneous Speech to Speech Translation
This work addresses the problem of enabling fluid cross-language conversations through on-device simultaneous speech-to-speech translation, representing an incremental advancement over existing methods.
The paper tackled the challenge of achieving accurate, real-time simultaneous speech-to-speech translation on mobile devices by introducing SimulTron, a lightweight direct model that surpasses Translatotron 2 in offline evaluations and improves upon Translatotron 1 in real-time evaluations, with superior BLEU scores and latency on the MuST-C dataset and successful deployment on a Pixel 7 Pro device.
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.