Quantum Approaches for Dysphonia Assessment in Small Speech Datasets

TL;DR

This paper compares quantum-classical hybrid neural networks with traditional CNNs for dysphonia assessment, demonstrating that QNNs perform better on small speech datasets.

Contribution

It introduces and evaluates a novel quantum-classical hybrid approach (QNNs) for speech disorder classification on limited data, outperforming CNNs.

Findings

QNNs outperform CNNs in accuracy on small speech datasets.

QNNs show greater stability across experiments.

Hybrid quantum-classical models are promising for medical audio analysis.

Abstract

Dysphonia, a prevalent medical condition, leads to voice loss, hoarseness, or speech interruptions. To assess it, researchers have been investigating various machine learning techniques alongside traditional medical assessments. Convolutional Neural Networks (CNNs) have gained popularity for their success in audio classification and speech recognition. However, the limited availability of speech data, poses a challenge for CNNs. This study evaluates the performance of CNNs against a novel hybrid quantum-classical approach, Quanvolutional Neural Networks (QNNs), which are well-suited for small datasets. The audio data was preprocessed into Mel spectrograms, comprising 243 training samples and 61 testing samples in total, and used in ten experiments. Four models were developed (two QNNs and two CNNs) with the second models incorporating additional layers to boost performance. The results revealed that QNN models consistently outperformed CNN models in accuracy and stability across most experiments.