Breeding Gender-aware Direct Speech Translation Systems

TL;DR

This paper explores methods to incorporate speaker gender information into direct speech translation models to improve gender translation accuracy, demonstrating significant performance gains over gender-unaware models.

Contribution

It introduces and compares approaches for integrating speaker gender cues into direct speech translation systems, addressing gender bias and enhancing translation accuracy.

Findings

Gender-aware models improve gender translation accuracy by up to 30 points.

Manual annotation of datasets with gender information enables effective training.

Gender-aware solutions outperform gender-unaware models in real-world scenarios.

Abstract

In automatic speech translation (ST), traditional cascade approaches involving separate transcription and translation steps are giving ground to increasingly competitive and more robust direct solutions. In particular, by translating speech audio data without intermediate transcription, direct ST models are able to leverage and preserve essential information present in the input (e.g. speaker's vocal characteristics) that is otherwise lost in the cascade framework. Although such ability proved to be useful for gender translation, direct ST is nonetheless affected by gender bias just like its cascade counterpart, as well as machine translation and numerous other natural language processing applications. Moreover, direct ST systems that exclusively rely on vocal biometric features as a gender cue can be unsuitable and potentially harmful for certain users. Going beyond speech signals, in this paper we compare different approaches to inform direct ST models about the speaker's gender and test their ability to handle gender translation from English into Italian and French. To this aim, we manually annotated large datasets with speakers' gender information and used them for experiments reflecting different possible real-world scenarios. Our results show that gender-aware direct ST solutions can significantly outperform strong - but gender-unaware - direct ST models. In particular, the translation of gender-marked words can increase up to 30 points in accuracy while preserving overall translation quality.