Comparison of voice features for Arabic speech recognition

Mansour Alsulaiman, Ghulam Muhammad, Zulfiqar Ali

Research output: Contribution to conferencePaper

8 Citations (Scopus)

Abstract

Selection of the speech feature for speech recognition has been investigated for languages other than Arabic. Arabic Language has its own characteristics hence some speech features may be more suited for Arabic speech recognition than the others. In this paper, some feature extraction techniques are explored to find the features that will give the highest speech recognition rate. Our investigation in this paper showed that Mel-Frequency Cepstral Coefficients (MFCC) gave the best result. We also look at using an operator well know in image processing field to modify the way we calculate MFCC, this results in a new feature that we call LBPCC. We propose the way we use this operator. Then we conduct some experiments to test the proposed feature.

Conference

Conference2011 6th International Conference on Digital Information Management, ICDIM 2011
CountryAustralia
Cityvar.pagings
Period26/09/1128/09/11

Fingerprint

Speech recognition
Feature extraction
Image processing
Experiments
Operator
Coefficients
Language

Keywords

  • ANN
  • Arabic speech recognition
  • HMM
  • LBPCC
  • LPC
  • MFCC

Cite this

Alsulaiman, M., Muhammad, G., & Ali, Z. (2011). Comparison of voice features for Arabic speech recognition. 90-95. Paper presented at 2011 6th International Conference on Digital Information Management, ICDIM 2011, var.pagings, Australia. https://doi.org/10.1109/ICDIM.2011.6093369
Alsulaiman, Mansour ; Muhammad, Ghulam ; Ali, Zulfiqar. / Comparison of voice features for Arabic speech recognition. Paper presented at 2011 6th International Conference on Digital Information Management, ICDIM 2011, var.pagings, Australia.6 p.
@conference{aa2624f9160a43bfad88da143714e62a,
title = "Comparison of voice features for Arabic speech recognition",
abstract = "Selection of the speech feature for speech recognition has been investigated for languages other than Arabic. Arabic Language has its own characteristics hence some speech features may be more suited for Arabic speech recognition than the others. In this paper, some feature extraction techniques are explored to find the features that will give the highest speech recognition rate. Our investigation in this paper showed that Mel-Frequency Cepstral Coefficients (MFCC) gave the best result. We also look at using an operator well know in image processing field to modify the way we calculate MFCC, this results in a new feature that we call LBPCC. We propose the way we use this operator. Then we conduct some experiments to test the proposed feature.",
keywords = "ANN, Arabic speech recognition, HMM, LBPCC, LPC, MFCC",
author = "Mansour Alsulaiman and Ghulam Muhammad and Zulfiqar Ali",
year = "2011",
month = "12",
day = "22",
doi = "10.1109/ICDIM.2011.6093369",
language = "English",
pages = "90--95",
note = "2011 6th International Conference on Digital Information Management, ICDIM 2011 ; Conference date: 26-09-2011 Through 28-09-2011",

}

Alsulaiman, M, Muhammad, G & Ali, Z 2011, 'Comparison of voice features for Arabic speech recognition' Paper presented at 2011 6th International Conference on Digital Information Management, ICDIM 2011, var.pagings, Australia, 26/09/11 - 28/09/11, pp. 90-95. https://doi.org/10.1109/ICDIM.2011.6093369

Comparison of voice features for Arabic speech recognition. / Alsulaiman, Mansour; Muhammad, Ghulam; Ali, Zulfiqar.

2011. 90-95 Paper presented at 2011 6th International Conference on Digital Information Management, ICDIM 2011, var.pagings, Australia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Comparison of voice features for Arabic speech recognition

AU - Alsulaiman, Mansour

AU - Muhammad, Ghulam

AU - Ali, Zulfiqar

PY - 2011/12/22

Y1 - 2011/12/22

N2 - Selection of the speech feature for speech recognition has been investigated for languages other than Arabic. Arabic Language has its own characteristics hence some speech features may be more suited for Arabic speech recognition than the others. In this paper, some feature extraction techniques are explored to find the features that will give the highest speech recognition rate. Our investigation in this paper showed that Mel-Frequency Cepstral Coefficients (MFCC) gave the best result. We also look at using an operator well know in image processing field to modify the way we calculate MFCC, this results in a new feature that we call LBPCC. We propose the way we use this operator. Then we conduct some experiments to test the proposed feature.

AB - Selection of the speech feature for speech recognition has been investigated for languages other than Arabic. Arabic Language has its own characteristics hence some speech features may be more suited for Arabic speech recognition than the others. In this paper, some feature extraction techniques are explored to find the features that will give the highest speech recognition rate. Our investigation in this paper showed that Mel-Frequency Cepstral Coefficients (MFCC) gave the best result. We also look at using an operator well know in image processing field to modify the way we calculate MFCC, this results in a new feature that we call LBPCC. We propose the way we use this operator. Then we conduct some experiments to test the proposed feature.

KW - ANN

KW - Arabic speech recognition

KW - HMM

KW - LBPCC

KW - LPC

KW - MFCC

UR - http://www.scopus.com/inward/record.url?scp=83755162583&partnerID=8YFLogxK

U2 - 10.1109/ICDIM.2011.6093369

DO - 10.1109/ICDIM.2011.6093369

M3 - Paper

SP - 90

EP - 95

ER -

Alsulaiman M, Muhammad G, Ali Z. Comparison of voice features for Arabic speech recognition. 2011. Paper presented at 2011 6th International Conference on Digital Information Management, ICDIM 2011, var.pagings, Australia. https://doi.org/10.1109/ICDIM.2011.6093369