Enhancing expressivity transfer in textless speech-to-speech translation

Textless speech-to-speech translation systems are rapidly advancing, thanks to the integration of self-supervised learning techniques. However, existing state-of-the-art systems fall short when it comes to capturing and transferring expressivity accurately across different languages. Expressivity pl...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Duret, Jarod, O'Brien, Benjamin, Estève, Yannick, Parcollet, Titouan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.10.2023
Subjects
Emotions
Languages
Self-supervised learning
Speech
Online AccessGet full text

Cover

More Information
Summary:Textless speech-to-speech translation systems are rapidly advancing, thanks to the integration of self-supervised learning techniques. However, existing state-of-the-art systems fall short when it comes to capturing and transferring expressivity accurately across different languages. Expressivity plays a vital role in conveying emotions, nuances, and cultural subtleties, thereby enhancing communication across diverse languages. To address this issue this study presents a novel method that operates at the discrete speech unit level and leverages multilingual emotion embeddings to capture language-agnostic information. Specifically, we demonstrate how these embeddings can be used to effectively predict the pitch and duration of speech units in the target language. Through objective and subjective experiments conducted on a French-to-English translation task, our findings highlight the superior expressivity transfer achieved by our approach compared to current state-of-the-art systems.
ISSN:2331-8422