Voice Disorder Detection Using Long Short Term Memory (LSTM) Model

TL;DR

This paper presents an LSTM-based approach for detecting voice disorders from audio data, aiming to improve early diagnosis with high specificity and promising sensitivity in a resource-efficient manner.

Contribution

It introduces a novel application of LSTM for voice disorder detection and evaluates its effectiveness on real-world data without relying on labeled training samples.

Findings

Achieved 97% specificity in voice disorder detection

Obtained 22% sensitivity, indicating room for improvement

Reached 56% unweighted average recall on test data

Abstract

Automated detection of voice disorders with computational methods is a recent research area in the medical domain since it requires a rigorous endoscopy for the accurate diagnosis. Efficient screening methods are required for the diagnosis of voice disorders so as to provide timely medical facilities in minimal resources. Detecting Voice disorder using computational methods is a challenging problem since audio data is continuous due to which extracting relevant features and applying machine learning is hard and unreliable. This paper proposes a Long short term memory model (LSTM) to detect pathological voice disorders and evaluates its performance in a real 400 testing samples without any labels. Different feature extraction methods are used to provide the best set of features before applying LSTM model for classification. The paper describes the approach and experiments that show promising results with 22% sensitivity, 97% specificity and 56% unweighted average recall.