MU Digital Repository
Logo

k-Means Nearest Neighbor Classifier for Voice Pathology

Ananthakrishna, T and Shama, Kumara and Cholayya, Niranjan U. (2004) k-Means Nearest Neighbor Classifier for Voice Pathology. In: IEEE India Annual Conference INDICON 2004, December 20-22, IIT Kharaghpur.

[img] PDF
01497770.pdf - Published Version
Restricted to Registered users only

Download (522kB) | Request a copy

Abstract

The noninvasive acoustical analysis of normal and pathological voices help speech specialists to perform accurate diagnose of diseases. Pathological voices show higher vocal noise level due to malfunctioning of vocal cords. Addition of noise component in speech has found to change the spectral properties. In this study, we show the use of energy spectrum which is obtained from 2l-channel filter-bank outputs, for the classification of pathological voices. A simple k-means nearest neighbor classifier based on spectral distance is designed and a good classification results have been reported.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Voice pathology, Critical band frequency, Spectral distance, k-meaas NN Classifier.
Subjects: Engineering > MIT Manipal > Electronics and Communication
Depositing User: Anantha krishna T
Date Deposited: 11 Jul 2011 05:09
Last Modified: 25 Feb 2015 05:15
URI: http://eprints.manipal.edu/id/eprint/621

Actions (login required)

View Item View Item