Enregistré dans:
Détails bibliographiques
Auteurs principaux: Deshpande, Gauri, Battula, Harish, Panda, Ashish, Kopparapu, Sunil Kumar
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.02669
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917118939758592
author Deshpande, Gauri
Battula, Harish
Panda, Ashish
Kopparapu, Sunil Kumar
author_facet Deshpande, Gauri
Battula, Harish
Panda, Ashish
Kopparapu, Sunil Kumar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02669
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SAND Challenge: Four Approaches for Dysartria Severity Classification
Deshpande, Gauri
Battula, Harish
Panda, Ashish
Kopparapu, Sunil Kumar
Sound
Artificial Intelligence
Machine Learning
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.
title SAND Challenge: Four Approaches for Dysartria Severity Classification
topic Sound
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2512.02669