Electroglottographic signal acquisition and neural network based classification for pathology

S. G. Nayak; Jagdish Nayak

Electroglottographic signal acquisition and neural network based classification for pathology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

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.

Original language	English
Title of host publication	3rd Kuala Lumpur International Conference on Biomedical Engineering 2006
Publisher	Springer Verlag
Pages	59-62
Number of pages	4
Volume	15
ISBN (Electronic)	9783540680161
Publication status	Published - 2007
Event	3rd Kuala Lumpur International Conference on Biomedical Engineering, Biomed 2006 - Kuala Lumpur, Malaysia Duration: 11-12-2006 → 14-12-2006

Conference

Conference	3rd Kuala Lumpur International Conference on Biomedical Engineering, Biomed 2006
Country/Territory	Malaysia
City	Kuala Lumpur
Period	11-12-06 → 14-12-06

All Science Journal Classification (ASJC) codes

Biomedical Engineering
Bioengineering

Cite this

@inproceedings{4f849a09025a402d934bc33ee4d5b3e0,

title = "Electroglottographic signal acquisition and neural network based classification for pathology",

abstract = "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.",

author = "Nayak, {S. G.} and Jagdish Nayak",

year = "2007",

language = "English",

volume = "15",

pages = "59--62",

booktitle = "3rd Kuala Lumpur International Conference on Biomedical Engineering 2006",

publisher = "Springer Verlag",

address = "Germany",

note = "3rd Kuala Lumpur International Conference on Biomedical Engineering, Biomed 2006 ; Conference date: 11-12-2006 Through 14-12-2006",

}

TY - GEN

T1 - Electroglottographic signal acquisition and neural network based classification for pathology

AU - Nayak, S. G.

AU - Nayak, Jagdish

PY - 2007

Y1 - 2007

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84928893790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928893790&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84928893790

VL - 15

SP - 59

EP - 62

BT - 3rd Kuala Lumpur International Conference on Biomedical Engineering 2006

PB - Springer Verlag

T2 - 3rd Kuala Lumpur International Conference on Biomedical Engineering, Biomed 2006

Y2 - 11 December 2006 through 14 December 2006

ER -

Electroglottographic signal acquisition and neural network based classification for pathology

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this