Intelligibility Assessment of Dysarthric Speech Using Extreme Learning Machine

Artificial neural networks are known for their superior performance in many applications. Weights obtained during training are fine-tuned to the training data used. As a result the performance is reduced when tested with unseen data. Also, the use of backpropagation algorithms used in conventional n...

Full description

Saved in:
Bibliographic Details
Published in2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET) pp. 208 - 212
Main Authors M., Chandrashekar H., Karjigi, Veena, N., Sreedevi
Format Conference Proceeding
LanguageEnglish
Published IEEE 24.03.2022
Subjects
Artificial neural network
Artificial neural networks
Cepstral analysis
Cepstral coefficients
Dysarthric speech
Extreme learning machine
Extreme learning machines
Intelligibility assessment
Training
Training data
Wireless communication
Online AccessGet full text

Cover

More Information
Summary:Artificial neural networks are known for their superior performance in many applications. Weights obtained during training are fine-tuned to the training data used. As a result the performance is reduced when tested with unseen data. Also, the use of backpropagation algorithms used in conventional neural networks is time consuming. Extreme learning machine classifiers are known for better generalization and quicker training compared to the neural networks with back propagation. In this work, the performance of the above mentioned classifiers on both seen and unseen data when used with cepstral coefficients is compared.
DOI:10.1109/WiSPNET54241.2022.9767182