Automatic detection of speech disorder in dysarthria using extended speech feature extraction and neural networks classification

Research output: Contribution to conferencePaper

Abstract

This paper presents an automatic detection of Dysarthria, a motor speech disorder, using extended speech features called Centroid Formants. Centroid Formants are the weighted averages of the formants extracted from a speech signal. This involves extraction of the first four formants of a speech signal and averaging their weighted values. The weights are determined by the peak energies of the bands of frequency resonance, formants. The resulting weighted averages are called the Centroid Formants. In our proposed methodology, these centroid formants are used to automatically detect Dysarthric speech using neural network classification technique. The experimental results recorded after testing this algorithm are presented. The experimental data consists of 200 speech samples from 10 Dysarthric Speakers and 200 speech samples from 10 age-matched healthy speakers. The experimental results show a high performance using neural networks classification. A possible future research related to this work is the use of these extended features in speaker identification and recognition of disordered speech.

Conference

ConferenceThe 3rd International Conference on Intelligent Signal Processing
Abbreviated titleISP 2017
CountryUnited Kingdom
CityLondon
Period4/12/175/12/17
Internet address

Fingerprint

Speech Disorders
Dysarthria
Feature extraction
Neural networks
Weights and Measures
Testing

Keywords

  • dysarthria
  • speech disorder
  • neural networks
  • centroid formants

Cite this

@conference{0a5b9853a6394a19b28f504be7ffadae,
title = "Automatic detection of speech disorder in dysarthria using extended speech feature extraction and neural networks classification",
abstract = "This paper presents an automatic detection of Dysarthria, a motor speech disorder, using extended speech features called Centroid Formants. Centroid Formants are the weighted averages of the formants extracted from a speech signal. This involves extraction of the first four formants of a speech signal and averaging their weighted values. The weights are determined by the peak energies of the bands of frequency resonance, formants. The resulting weighted averages are called the Centroid Formants. In our proposed methodology, these centroid formants are used to automatically detect Dysarthric speech using neural network classification technique. The experimental results recorded after testing this algorithm are presented. The experimental data consists of 200 speech samples from 10 Dysarthric Speakers and 200 speech samples from 10 age-matched healthy speakers. The experimental results show a high performance using neural networks classification. A possible future research related to this work is the use of these extended features in speaker identification and recognition of disordered speech.",
keywords = "dysarthria, speech disorder, neural networks, centroid formants",
author = "Ijitona, {T B} and Soraghan, {J J} and A Lowit and G Di-Caterina and H Yue",
year = "2017",
month = "12",
day = "4",
language = "English",
note = "The 3rd International Conference on Intelligent Signal Processing, ISP 2017 ; Conference date: 04-12-2017 Through 05-12-2017",
url = "http://events.theiet.org/isp/",

}

Ijitona, TB, Soraghan, JJ, Lowit, A, Di-Caterina, G & Yue, H 2017, 'Automatic detection of speech disorder in dysarthria using extended speech feature extraction and neural networks classification' Paper presented at The 3rd International Conference on Intelligent Signal Processing, London, United Kingdom, 4/12/17 - 5/12/17, .

Automatic detection of speech disorder in dysarthria using extended speech feature extraction and neural networks classification. / Ijitona, T B; Soraghan, J J; Lowit, A; Di-Caterina, G; Yue, H.

2017. Paper presented at The 3rd International Conference on Intelligent Signal Processing, London, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Automatic detection of speech disorder in dysarthria using extended speech feature extraction and neural networks classification

AU - Ijitona, T B

AU - Soraghan, J J

AU - Lowit, A

AU - Di-Caterina, G

AU - Yue, H

PY - 2017/12/4

Y1 - 2017/12/4

N2 - This paper presents an automatic detection of Dysarthria, a motor speech disorder, using extended speech features called Centroid Formants. Centroid Formants are the weighted averages of the formants extracted from a speech signal. This involves extraction of the first four formants of a speech signal and averaging their weighted values. The weights are determined by the peak energies of the bands of frequency resonance, formants. The resulting weighted averages are called the Centroid Formants. In our proposed methodology, these centroid formants are used to automatically detect Dysarthric speech using neural network classification technique. The experimental results recorded after testing this algorithm are presented. The experimental data consists of 200 speech samples from 10 Dysarthric Speakers and 200 speech samples from 10 age-matched healthy speakers. The experimental results show a high performance using neural networks classification. A possible future research related to this work is the use of these extended features in speaker identification and recognition of disordered speech.

AB - This paper presents an automatic detection of Dysarthria, a motor speech disorder, using extended speech features called Centroid Formants. Centroid Formants are the weighted averages of the formants extracted from a speech signal. This involves extraction of the first four formants of a speech signal and averaging their weighted values. The weights are determined by the peak energies of the bands of frequency resonance, formants. The resulting weighted averages are called the Centroid Formants. In our proposed methodology, these centroid formants are used to automatically detect Dysarthric speech using neural network classification technique. The experimental results recorded after testing this algorithm are presented. The experimental data consists of 200 speech samples from 10 Dysarthric Speakers and 200 speech samples from 10 age-matched healthy speakers. The experimental results show a high performance using neural networks classification. A possible future research related to this work is the use of these extended features in speaker identification and recognition of disordered speech.

KW - dysarthria

KW - speech disorder

KW - neural networks

KW - centroid formants

UR - http://events.theiet.org/isp/index.cfm?utm_source=redirect&utm_medium=any&utm_campaign=isp

M3 - Paper

ER -