Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech

TL;DR

This paper investigates diffusion-based speech enhancement techniques to improve the intelligibility and recognition accuracy of dysarthric speech, comparing them with traditional methods through subjective and objective evaluations.

Contribution

It introduces the application of diffusion models for dysarthric speech enhancement and evaluates their effectiveness in improving speech quality and ASR performance.

Findings

Diffusion-based methods improve speech intelligibility.

Enhanced speech leads to better ASR accuracy.

Diffusion models outperform traditional signal processing techniques.

Abstract

Dysarthric speech poses significant challenges for automatic speech recognition (ASR) systems due to its high variability and reduced intelligibility. In this work we explore the use of diffusion models for dysarthric speech enhancement, which is based on the hypothesis that using diffusion-based speech enhancement moves the distribution of dysarthric speech closer to that of typical speech, which could potentially improve dysarthric speech recognition performance. We assess the effect of two diffusion-based and one signal-processing-based speech enhancement algorithms on intelligibility and speech quality of two English dysarthric speech corpora. We applied speech enhancement to both typical and dysarthric speech and evaluate the ASR performance using Whisper-Turbo, and the subjective and objective speech quality of the original and enhanced dysarthric speech. We also fine-tuned Whisper-Turbo on the enhanced speech to assess its impact on recognition performance.