Contrastive Feedback Mechanism for Simultaneous Speech Translation

TL;DR

This paper introduces the contrastive feedback mechanism (CFM) for simultaneous speech translation, leveraging unstable predictions as feedback to enhance translation quality across multiple languages.

Contribution

The novel CFM method uses contrastive learning to utilize unstable predictions as feedback, improving SST performance beyond existing decision policies.

Findings

CFM improves translation quality across 8 languages.

Experiments show consistent gains with 3 state-of-the-art policies.

CFM effectively mitigates unstable prediction impacts.

Abstract

Recent advances in simultaneous speech translation (SST) focus on the decision policies that enable the use of offline-trained ST models for simultaneous inference. These decision policies not only control the quality-latency trade-off in SST but also mitigate the impact of unstable predictions on translation quality by delaying translation for more context or discarding these predictions through stable hypothesis detection. However, these policies often overlook the potential benefits of utilizing unstable predictions. We introduce the contrastive feedback mechanism (CFM) for SST, a novel method that leverages these unstable predictions as feedback to improve translation quality. CFM guides the system to eliminate undesired model behaviors from these predictions through a contrastive objective. The experiments on 3 state-of-the-art decision policies across 8 languages in the MuST-C v1.0 dataset show that CFM effectively improves the performance of SST.