Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation

Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language speech into sequences of discrete representations in the targ...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Duret, Jarod, Estève, Yannick, Parcollet, Titouan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 08.07.2024
Subjects
Automatic speech recognition
Emotion recognition
Machine learning
Self-supervised learning
State-of-the-art reviews
Task complexity
Online AccessGet full text

Cover

More Information
Summary:Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language speech into sequences of discrete representations in the target language, the criteria for selecting these target speech units remains an open question. This work explores the selection process through a study of downstream tasks such as automatic speech recognition, speech synthesis, speaker recognition, and emotion recognition. Interestingly, our findings reveal a discrepancy in the optimization of discrete speech units: units that perform well in resynthesis performance do not necessarily correlate with those that enhance translation efficacy. This discrepancy underscores the nuanced complexity of target feature selection and its impact on the overall performance of speech-to-speech translation systems.
ISSN:2331-8422