K-means nearest neighbor classifier for voice pathology

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Citations (Scopus)

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 21-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.

Original languageEnglish
Title of host publicationProceedings of the IEEE INDICON 2004 - 1st India Annual Conference
Pages352-354
Number of pages3
Publication statusPublished - 2004
EventIEEE INDICON 2004 - 1st India Annual Conference - Kharagpur, India
Duration: 20-12-200422-12-2004

Conference

ConferenceIEEE INDICON 2004 - 1st India Annual Conference
CountryIndia
CityKharagpur
Period20-12-0422-12-04

Fingerprint

Pathology
Classifiers
Filter banks

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Ananthakrishna, T., Shama, K., & Niranjan, U. C. (2004). K-means nearest neighbor classifier for voice pathology. In Proceedings of the IEEE INDICON 2004 - 1st India Annual Conference (pp. 352-354)
Ananthakrishna, T. ; Shama, Kumara ; Niranjan, U. C. / K-means nearest neighbor classifier for voice pathology. Proceedings of the IEEE INDICON 2004 - 1st India Annual Conference. 2004. pp. 352-354
@inproceedings{98a8721a03cf4802bf16a648fb578a99,
title = "K-means nearest neighbor classifier for voice pathology",
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 21-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.",
author = "T. Ananthakrishna and Kumara Shama and Niranjan, {U. C.}",
year = "2004",
language = "English",
isbn = "0780389093",
pages = "352--354",
booktitle = "Proceedings of the IEEE INDICON 2004 - 1st India Annual Conference",

}

Ananthakrishna, T, Shama, K & Niranjan, UC 2004, K-means nearest neighbor classifier for voice pathology. in Proceedings of the IEEE INDICON 2004 - 1st India Annual Conference. pp. 352-354, IEEE INDICON 2004 - 1st India Annual Conference, Kharagpur, India, 20-12-04.

K-means nearest neighbor classifier for voice pathology. / Ananthakrishna, T.; Shama, Kumara; Niranjan, U. C.

Proceedings of the IEEE INDICON 2004 - 1st India Annual Conference. 2004. p. 352-354.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - K-means nearest neighbor classifier for voice pathology

AU - Ananthakrishna, T.

AU - Shama, Kumara

AU - Niranjan, U. C.

PY - 2004

Y1 - 2004

N2 - 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 21-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.

AB - 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 21-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.

UR - http://www.scopus.com/inward/record.url?scp=28444443797&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28444443797&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780389093

SN - 9780780389090

SP - 352

EP - 354

BT - Proceedings of the IEEE INDICON 2004 - 1st India Annual Conference

ER -

Ananthakrishna T, Shama K, Niranjan UC. K-means nearest neighbor classifier for voice pathology. In Proceedings of the IEEE INDICON 2004 - 1st India Annual Conference. 2004. p. 352-354