Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models

TL;DR

This paper introduces Locate-and-Focus, a method that improves terminology translation in speech translation models by accurately locating terminology segments and associating relevant translation knowledge across audio and text modalities.

Contribution

It proposes a novel approach to locate terminology segments and integrate translation knowledge, reducing noise and enhancing terminology translation accuracy in speech translation models.

Findings

Effective localization of terminology segments within utterances.

Improved accuracy of terminology translation across datasets.

Maintains overall translation performance while enhancing terminology handling.

Abstract

Direct speech translation (ST) has garnered increasing attention nowadays, yet the accurate translation of terminology within utterances remains a great challenge. In this regard, current studies mainly concentrate on leveraging various translation knowledge into ST models. However, these methods often struggle with interference from irrelevant noise and can not fully utilize the translation knowledge. To address these issues, in this paper, we propose a novel Locate-and-Focus method for terminology translation. It first effectively locates the speech clips containing terminologies within the utterance to construct translation knowledge, minimizing irrelevant information for the ST model. Subsequently, it associates the translation knowledge with the utterance and hypothesis from both audio and textual modalities, allowing the ST model to better focus on translation knowledge during translation. Experimental results across various datasets demonstrate that our method effectively locates terminologies within utterances and enhances the success rate of terminology translation, while maintaining robust general translation performance.