SAND Challenge: Four Approaches for Dysartria Severity Classification
This work addresses dysarthria severity classification for medical speech analysis, presenting an incremental comparison of existing methods on a new dataset.
The paper tackled dysarthria severity classification by comparing four modeling approaches on a common dataset, finding that a feature-engineered XGBoost ensemble achieved the highest macro-F1 score of 0.86, while deep learning models like ViT, CNN, and BiLSTM attained competitive F1-scores of 0.70.
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.