EGG signal Classification using Principal Component Analysis

Nayak, Subramanya G and Puttamadappa, C (2009) EGG signal Classification using Principal Component Analysis. International Journal on Intelligent Electronic Systems, 3 (2).

[img] PDF
IJIES-Int.Journal-July-2009-1.pdf - Published Version
Restricted to Registered users only

Download (277kB) | 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. In this Electroglottography (EGG) signal acquisition, the electrodes are made of steel. They have the form of rectangles covering an area of 10.75 cm2. It is designed as a ring electrode encircling each of the two other electrodes. The electrodes are mounted on a flexible band whose length is adjusted to hold the electrodes in a steady position and to still allow the subject to comfortably speak and breathe naturally. The electrodes are mounted on a small holder which is pressed against the throat by hand. A signal generator supplies an AC sinusoidal current usually ranging from 2 MHz. The RF carrier signal is amplitude modulated by the modulating speech/ voice signal and the demodulated signal is extracted. The variations in the signal correspond to the vocal fold abduction/laryngeal movement. For normal and pathology conditions, the results are recorded. These values form a feature vector, which reveals information regarding pathology. Principal Component Analysis technique (PCA) is used for classification, giving successful results for the specific data set considered.

Item Type: Article
Uncontrolled Keywords: Electroglottography, Principal Component Analysis.
Subjects: Engineering > MIT Manipal > Electronics and Communication
Depositing User: MIT Library
Date Deposited: 02 Feb 2016 14:05
Last Modified: 02 Feb 2016 14:05

Actions (login required)

View Item View Item