A study on the impact of Self-Supervised Learning on automatic dysarthric speech assessment
This work addresses the problem of limited data for dysarthria assessment, offering incremental improvements for developing automated tools in speech pathology.
The study tackled the challenge of automating dysarthric speech assessment by evaluating self-supervised learning models on tasks like disease classification, word recognition, and intelligibility classification, showing that HuBERT improved accuracy by up to 61% compared to classical features.
Automating dysarthria assessments offers the opportunity to develop practical, low-cost tools that address the current limitations of manual and subjective assessments. Nonetheless, the small size of most dysarthria datasets makes it challenging to develop automated assessment. Recent research showed that speech representations from models pre-trained on large unlabelled data can enhance Automatic Speech Recognition (ASR) performance for dysarthric speech. We are the first to evaluate the representations from pre-trained state-of-the-art Self-Supervised models across three downstream tasks on dysarthric speech: disease classification, word recognition and intelligibility classification, and under three noise scenarios on the UA-Speech dataset. We show that HuBERT is the most versatile feature extractor across dysarthria classification, word recognition, and intelligibility classification, achieving respectively $+24.7\%, +61\%, \text{and} +7.2\%$ accuracy compared to classical acoustic features.