# Machine Learning Classifiers for Voice Health Assessment under Simulated Room Acoustics

## TL;DR

This paper studies how well machine learning models can detect voice disorders in different room acoustics, showing that data augmentation is key for real-world reliability.

## Contribution

The study introduces a method to evaluate ML classifiers for voice health under simulated room reverberation, emphasizing the need for data augmentation.

## Key findings

- Support Vector Machine and k-Nearest Neighbors showed reliable accuracy in short reverberation conditions.
- Random Forest had the highest accuracy on clean data but failed to generalize in simulated room conditions.
- Training on augmented data is crucial for robust voice disorder detection in real-world settings.

## Abstract

Machine learning (ML) robustness for voice disorder detection was evaluated using reverberation-augmented recordings, highlighting data quality’s impact. Common vocal health assessment voice features from steady vowel samples (135 pathological, 49 controls) were used to train and test six ML classifiers. Detection performance was evaluated using clean and 2 simulated room reverberation situations (short=0.48s, long=1.82s). Support Vector Machine and k-Nearest Neighbors demonstrated reliable accuracy under short/acceptable reverberation, while Random Forest achieved the highest accuracy on clean data but lacked generalizability in augmented room conditions. Training/testing ML models on augmented data is essential to enhance their reliability in real-world voice assessments.