SAND Challenge: Four Approaches for Dysartria Severity Classification

TL;DR

This study compares four different modeling approaches—deep learning and ensemble methods—for classifying dysarthria severity from speech data, highlighting their performance and complementary strengths in a unified framework.

Contribution

The paper provides a comprehensive comparison of four modeling approaches for dysarthria severity classification, including a novel ensemble method and insights into their relative effectiveness.

Findings

XGBoost ensemble achieves highest macro-F1 (0.86)

Deep learning models attain competitive F1-scores (~0.70)

Models offer complementary insights into dysarthria classification

Abstract

This paper presents a unified study of four distinct modeling approaches for classifying dysarthria severity in the Speech Analysis for Neurodegenerative Diseases (SAND) challenge. All models tackle the same five class classification task using a common dataset of speech recordings. We investigate: (1) a ViT-OF method leveraging a Vision Transformer on spectrogram images, (2) a 1D-CNN approach using eight 1-D CNN's with majority-vote fusion, (3) a BiLSTM-OF approach using nine BiLSTM models with majority vote fusion, and (4) a Hierarchical XGBoost ensemble that combines glottal and formant features through a two stage learning framework. Each method is described, and their performances on a validation set of 53 speakers are compared. Results show that while the feature-engineered XGBoost ensemble achieves the highest macro-F1 (0.86), the deep learning models (ViT, CNN, BiLSTM) attain competitive F1-scores (0.70) and offer complementary insights into the problem.