From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation

TL;DR

This paper proposes latency reduction strategies for incremental speech synthesis in real-time speech-to-speech translation, focusing on minimizing initial delay and optimizing speech duration to improve responsiveness without quality loss.

Contribution

It introduces methods to reduce latency by adapting upstream translation for lookahead and applying duration-scaling, achieving significant improvements in real-time speech translation.

Findings

Latency reduced by 0.2-0.5 seconds

Maintained speech translation quality

Effective duration-scaling approach

Abstract

Speech-to-speech translation (S2ST) converts input speech to speech in another language. A challenge of delivering S2ST in real time is the accumulated delay between the translation and speech synthesis modules. While recently incremental text-to-speech (iTTS) models have shown large quality improvements, they typically require additional future text inputs to reach optimal performance. In this work, we minimize the initial waiting time of iTTS by adapting the upstream speech translator to generate high-quality pseudo lookahead for the speech synthesizer. After mitigating the initial delay, we demonstrate that the duration of synthesized speech also plays a crucial role on latency. We formalize this as a latency metric and then present a simple yet effective duration-scaling approach for latency reduction. Our approaches consistently reduce latency by 0.2-0.5 second without sacrificing speech translation quality.