Towards detecting the pathological subharmonic voicing with fully convolutional neural networks

TL;DR

This paper proposes a deep learning approach using fully convolutional neural networks trained on synthetic voice signals to reliably detect subharmonic phonation, a marker of voice disorders, achieving over 98% accuracy in synthetic tests.

Contribution

It introduces a novel CNN-based method trained on synthetic data for detecting subharmonic voice signals, addressing a challenging problem in voice disorder analysis.

Findings

Over 98% classification accuracy on synthetic data

Encouraging results on real sustained vowel recordings

Identifies areas for future improvement

Abstract

Many voice disorders induce subharmonic phonation, but voice signal analysis is currently lacking a technique to detect the presence of subharmonics reliably. Distinguishing subharmonic phonation from normal phonation is a challenging task as both are nearly periodic phenomena. Subharmonic phonation adds cyclical variations to the normal glottal cycles. Hence, the estimation of subharmonic period requires a wholistic analysis of the signals. Deep learning is an effective solution to this type of complex problem. This paper describes fully convolutional neural networks which are trained with synthesized subharmonic voice signals to classify the subharmonic periods. Synthetic evaluation shows over 98% classification accuracy, and assessment of sustained vowel recordings demonstrates encouraging outcomes as well as the areas for future improvements.