Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Liming, Gong, Yuan, Dawalatabad, Nauman, Vilela, Marco, Placek, Katerina, Tracey, Brian, Gong, Yishu, Premasiri, Alan, Vieira, Fernando, Glass, James
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2406.18625
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913406183800832
author Wang, Liming
Gong, Yuan
Dawalatabad, Nauman
Vilela, Marco
Placek, Katerina
Tracey, Brian
Gong, Yishu
Premasiri, Alan
Vieira, Fernando
Glass, James
author_facet Wang, Liming
Gong, Yuan
Dawalatabad, Nauman
Vilela, Marco
Placek, Katerina
Tracey, Brian
Gong, Yishu
Premasiri, Alan
Vieira, Fernando
Glass, James
contents Automatic prediction of amyotrophic lateral sclerosis (ALS) disease progression provides a more efficient and objective alternative than manual approaches. We propose ALS longitudinal speech transformer (ALST), a neural network-based automatic predictor of ALS disease progression from longitudinal speech recordings of ALS patients. By taking advantage of high-quality pretrained speech features and longitudinal information in the recordings, our best model achieves 91.0\% AUC, improving upon the previous best model by 5.6\% relative on the ALS TDI dataset. Careful analysis reveals that ALST is capable of fine-grained and interpretable predictions of ALS progression, especially for distinguishing between rarer and more severe cases. Code is publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18625
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automatic Prediction of Amyotrophic Lateral Sclerosis Progression using Longitudinal Speech Transformer
Wang, Liming
Gong, Yuan
Dawalatabad, Nauman
Vilela, Marco
Placek, Katerina
Tracey, Brian
Gong, Yishu
Premasiri, Alan
Vieira, Fernando
Glass, James
Sound
Artificial Intelligence
Audio and Speech Processing
Automatic prediction of amyotrophic lateral sclerosis (ALS) disease progression provides a more efficient and objective alternative than manual approaches. We propose ALS longitudinal speech transformer (ALST), a neural network-based automatic predictor of ALS disease progression from longitudinal speech recordings of ALS patients. By taking advantage of high-quality pretrained speech features and longitudinal information in the recordings, our best model achieves 91.0\% AUC, improving upon the previous best model by 5.6\% relative on the ALS TDI dataset. Careful analysis reveals that ALST is capable of fine-grained and interpretable predictions of ALS progression, especially for distinguishing between rarer and more severe cases. Code is publicly available.
title Automatic Prediction of Amyotrophic Lateral Sclerosis Progression using Longitudinal Speech Transformer
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2406.18625