Related Experiment Video
Updated: Aug 11, 2026
12:43
A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis (ALS)
Published on: February 21, 2011
Automated Detection of Motor Speech Disorders and Subtype Classification
Fenqi Wang1, Rene L Utianski1, Leland R Barnard1
1Neurology, Mayo Clinic, Rochester, MN.
Medrxiv : the Preprint Server for Health Sciences
|July 30, 2026
Summary
Automated speech analysis can detect motor speech disorders (MSDs), early neurological disease signs. Advanced models like HuBERT show high accuracy in binary classification, offering a promising clinical tool.
Area of Science:
- Neurology
- Speech-Language Pathology
- Computational Linguistics
Background:
- Motor speech disorders (MSDs) are crucial early indicators of neurological conditions.
- Access to expert speech analysis is limited to specialized centers.
- Automated speech analysis presents a scalable solution for MSD detection.
Purpose of the Study:
- To compare different automated speech analysis models for MSD classification.
- To evaluate model performance on clinically relevant metrics using independent datasets.
- To assess the utility of static acoustic, Phonet, and self-supervised pretrained models.
Main Methods:
- Trained and evaluated logistic regression, GRUs, Phonet features, HuBERT, and SSAST models on 583 speech samples.
- Utilized binary and multi-label classification for MSDs and subtypes.
- Assessed models using validation AUC and tested on two independent datasets.
Main Results:
- Pretrained and Phonet-based models significantly outperformed static acoustic features.
- HuBERT achieved the highest AUC (0.95) for binary classification, with Phonet-derived GRUs performing comparably (0.94).
- Models demonstrated good generalization to independent datasets for binary classification, but multi-label classification showed reduced stability.
Conclusions:
- Automated detection of MSDs is feasible and shows clinical promise.
- Binary classification models generalize effectively to new data.
- Multi-label classification for MSD subtypes requires further refinement for consistent performance across datasets.
