For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Deep Learning Approaches for Pathological Voice Detection Using Heterogeneous Parameters
JiYeoun LEE Hee-Jin CHOI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2020/08/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Speech and Hearing
pathological voice detection, feedforward neural network, convolutional neural network, higher-order statistics, deep learning method,
Full Text: PDF(589.8KB)>>
We propose a deep learning-based model for classifying pathological voices using a convolutional neural network and a feedforward neural network. The model uses combinations of heterogeneous parameters, including mel-frequency cepstral coefficients, linear predictive cepstral coefficients and higher-order statistics. We validate the accuracy of this model using the Massachusetts Eye and Ear Infirmary (MEEI) voice disorder database and the Saarbruecken Voice Database (SVD). Our model achieved an accuracy of 99.3% for MEEI and 75.18% for SVD. This model achieved an accuracy that is 7.18% higher than that of competitive models in previous studies.