A Few-Shot Approach to Dysarthric Speech Intelligibility Level Classification Using Transformers

TL;DR

This paper presents a few-shot transformer-based model for classifying dysarthria and its intelligibility levels using limited data, achieving high accuracy and addressing data leakage issues in previous research.

Contribution

It introduces a novel few-shot learning approach with transformers for dysarthria classification and improves data handling to prevent leakage.

Findings

Achieved 85% accuracy on dysarthria detection

Model trained on 'words' dataset outperformed 'letters' and 'digits' datasets

Multiclass model reached 67% accuracy

Abstract

Dysarthria is a speech disorder that hinders communication due to difficulties in articulating words. Detection of dysarthria is important for several reasons as it can be used to develop a treatment plan and help improve a person's quality of life and ability to communicate effectively. Much of the literature focused on improving ASR systems for dysarthric speech. The objective of the current work is to develop models that can accurately classify the presence of dysarthria and also give information about the intelligibility level using limited data by employing a few-shot approach using a transformer model. This work also aims to tackle the data leakage that is present in previous studies. Our whisper-large-v2 transformer model trained on a subset of the UASpeech dataset containing medium intelligibility level patients achieved an accuracy of 85%, precision of 0.92, recall of 0.8 F1-score of 0.85, and specificity of 0.91. Experimental results also demonstrate that the model trained using the 'words' dataset performed better compared to the model trained on the 'letters' and 'digits' dataset. Moreover, the multiclass model achieved an accuracy of 67%.