Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation

TL;DR

This paper introduces a noise-robust, textless acoustic model for expressive speech-to-speech translation using self-supervised distillation, significantly improving performance in noisy conditions while maintaining quality in clean environments.

Contribution

The paper presents a novel self-supervised distillation approach for a textless acoustic model that enhances noise robustness in expressive S2ST systems.

Findings

Improved translation quality in noisy environments

Maintained competitive performance in clean environments

Effective noise-agnostic expressivity representation

Abstract

In this paper, we propose a textless acoustic model with a self-supervised distillation strategy for noise-robust expressive speech-to-speech translation (S2ST). Recently proposed expressive S2ST systems have achieved impressive expressivity preservation performances by cascading unit-to-speech (U2S) generator to the speech-to-unit translation model. However, these systems are vulnerable to the presence of noise in input speech, which is an assumption in real-world translation scenarios. To address this limitation, we propose a U2S generator that incorporates a distillation with no label (DINO) self-supervised training strategy into it's pretraining process. Because the proposed method captures noise-agnostic expressivity representation, it can generate qualified speech even in noisy environment. Objective and subjective evaluation results verified that the proposed method significantly improved the performance of the expressive S2ST system in noisy environments while maintaining competitive performance in clean environments.