Oriented and Interpolated Local Features for Speech Recognition of Vocal Fold Disordered Patients

Zulfiqar Ali, Ghulam Muhammad, Mansour Alsulaiman, Irraivan Elamvazuthi, Khalid Al-Mutib

Research output: Contribution to journalArticle

Abstract

A novel technique of oriented local features (OLF) for speech recognition has been introduced in this paper. A speech recognition system for dysphonic patients is implemented by application of the proposed technique. The developed system is evaluated by performing the training in three different ways: (a) with pathological samples, (b) with normal samples, and (c) with pathological and normal samples together. We compare the performance of the proposed feature with the most widely used speech feature in speech recognition, i.e., Mel-frequency cepstral coefficients. The Hidden Markov model is used for recognizing the speech. The proposed technique achieved a 94.98% recognition rate, which is almost identical to the recognition rate of 95.45% obtained with MFCC.
LanguageEnglish
Pages1-11
Number of pages9
JournalInternational Journal for Computers and Their Applications
Volume22
Issue number1
Publication statusPublished - 31 Mar 2015

Fingerprint

Speech recognition
Hidden Markov models

Keywords

  • Vocal fold disorders
  • Automatic speech recognition
  • Arabic digits
  • MFCC
  • HMM

Cite this

Ali, Zulfiqar ; Muhammad, Ghulam ; Alsulaiman, Mansour ; Elamvazuthi, Irraivan ; Al-Mutib, Khalid. / Oriented and Interpolated Local Features for Speech Recognition of Vocal Fold Disordered Patients. In: International Journal for Computers and Their Applications. 2015 ; Vol. 22, No. 1. pp. 1-11.
@article{1fccf719b49b4714917347feb9057caa,
title = "Oriented and Interpolated Local Features for Speech Recognition of Vocal Fold Disordered Patients",
abstract = "A novel technique of oriented local features (OLF) for speech recognition has been introduced in this paper. A speech recognition system for dysphonic patients is implemented by application of the proposed technique. The developed system is evaluated by performing the training in three different ways: (a) with pathological samples, (b) with normal samples, and (c) with pathological and normal samples together. We compare the performance of the proposed feature with the most widely used speech feature in speech recognition, i.e., Mel-frequency cepstral coefficients. The Hidden Markov model is used for recognizing the speech. The proposed technique achieved a 94.98{\%} recognition rate, which is almost identical to the recognition rate of 95.45{\%} obtained with MFCC.",
keywords = "Vocal fold disorders, Automatic speech recognition, Arabic digits, MFCC, HMM",
author = "Zulfiqar Ali and Ghulam Muhammad and Mansour Alsulaiman and Irraivan Elamvazuthi and Khalid Al-Mutib",
note = "Author started at Ulster 2019",
year = "2015",
month = "3",
day = "31",
language = "English",
volume = "22",
pages = "1--11",
journal = "International Journal for Computers and Their Applications",
issn = "1076-5204",
number = "1",

}

Oriented and Interpolated Local Features for Speech Recognition of Vocal Fold Disordered Patients. / Ali, Zulfiqar; Muhammad, Ghulam; Alsulaiman, Mansour ; Elamvazuthi, Irraivan; Al-Mutib, Khalid.

In: International Journal for Computers and Their Applications, Vol. 22, No. 1, 31.03.2015, p. 1-11.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Oriented and Interpolated Local Features for Speech Recognition of Vocal Fold Disordered Patients

AU - Ali, Zulfiqar

AU - Muhammad, Ghulam

AU - Alsulaiman, Mansour

AU - Elamvazuthi, Irraivan

AU - Al-Mutib, Khalid

N1 - Author started at Ulster 2019

PY - 2015/3/31

Y1 - 2015/3/31

N2 - A novel technique of oriented local features (OLF) for speech recognition has been introduced in this paper. A speech recognition system for dysphonic patients is implemented by application of the proposed technique. The developed system is evaluated by performing the training in three different ways: (a) with pathological samples, (b) with normal samples, and (c) with pathological and normal samples together. We compare the performance of the proposed feature with the most widely used speech feature in speech recognition, i.e., Mel-frequency cepstral coefficients. The Hidden Markov model is used for recognizing the speech. The proposed technique achieved a 94.98% recognition rate, which is almost identical to the recognition rate of 95.45% obtained with MFCC.

AB - A novel technique of oriented local features (OLF) for speech recognition has been introduced in this paper. A speech recognition system for dysphonic patients is implemented by application of the proposed technique. The developed system is evaluated by performing the training in three different ways: (a) with pathological samples, (b) with normal samples, and (c) with pathological and normal samples together. We compare the performance of the proposed feature with the most widely used speech feature in speech recognition, i.e., Mel-frequency cepstral coefficients. The Hidden Markov model is used for recognizing the speech. The proposed technique achieved a 94.98% recognition rate, which is almost identical to the recognition rate of 95.45% obtained with MFCC.

KW - Vocal fold disorders

KW - Automatic speech recognition

KW - Arabic digits

KW - MFCC

KW - HMM

M3 - Article

VL - 22

SP - 1

EP - 11

JO - International Journal for Computers and Their Applications

T2 - International Journal for Computers and Their Applications

JF - International Journal for Computers and Their Applications

SN - 1076-5204

IS - 1

ER -