Electroglottographic Signal Acquisition and Neural Network based classification for Pathology

Nayak, Subramanya G and Nayak, Jagadish (2008) Electroglottographic Signal Acquisition and Neural Network based classification for Pathology. In: 3rd Kuala Lumpur International Conference on Biomedical 2008 , 2008, University of Malaya, Kuala Lumpur, Malaysia.

[img] PDF
D._GSN_CONF._PAPER.pdf - Published Version
Restricted to Registered users only

Download (147kB) | Request a copy


The method is used to register the laryngeal behavior indirectly by measuring change in the electrical impedance across the throat during speak or voice. The RF carrier signal is amplitude modulated by the modulating speech/ voice signal and the dc component from the demodulated signal is extracted. The variations in the dc component corresponds to the vocal fold abduction/laryngeal movement. For normal and pathology conditions the results are recorded. These values form a feature vector which reveal information regarding pathology. Then a classical multilayer feed forward neural network with back propagation algorithm is employed to serve as a classifier of the feature vector, giving 100% successful results for the specific data set considered.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Electroglottography (EGG), Artificial Neural Network (ANN) , Back propagation algorithm
Subjects: Engineering > MIT Manipal > Electronics and Communication
Depositing User: MIT Library
Date Deposited: 11 Apr 2013 10:34
Last Modified: 11 Apr 2013 10:34
URI: http://eprints.manipal.edu/id/eprint/79657

Actions (login required)

View Item View Item