Isolated Malay digit recognition using pattern recognition fusion of dynamic time warping and hidden Markov models

Syed Abdul Rahman Al-Haddad, Salina Abdul Samad, Aini Hussain, Khairul Anuar Ishak

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

This paper is presents a pattern recognition fusion method for isolated Malay digit recognition using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). The aim of the project is to increase the accuracy percentage of Malay speech recognition. This study proposes an algorithm for pattern recognition fusion of the recognition models. The endpoint detection, framing, normalization, Mel Frequency Cepstral Coefficient (MFCC) and vector quantization techniques are used to process speech samples to accomplish the recognition. Pattern recognition fusion method is then used to combine the results of DTW and HMM which uses weight mean vectors. The algorithm is tested on speech samples that are a part of a Malay corpus. This paper has shown that the fusion technique can be used to fuse the pattern recognition outputs of DTW and HMM. Furthermore it also introduced refinement normalization by using weight mean vector to get better performance with accuracy of 94% on pattern recognition fusion HMM and DTW. Unlikely accuracy for DTW and HMM, which is 80.5% and 90.7% respectively.

Original languageEnglish
Pages (from-to)714-720
Number of pages7
JournalAmerican Journal of Applied Sciences
Volume5
Issue number6
Publication statusPublished - 2008

Fingerprint

Hidden Markov models
Pattern recognition
Fusion reactions
Vector quantization
Electric fuses
Speech recognition

Keywords

  • Distance measurements and weight mean
  • Endpoint detection
  • Mel frequency cepstral coefficient
  • Vector quantization

ASJC Scopus subject areas

  • General

Cite this

Isolated Malay digit recognition using pattern recognition fusion of dynamic time warping and hidden Markov models. / Al-Haddad, Syed Abdul Rahman; Abdul Samad, Salina; Hussain, Aini; Ishak, Khairul Anuar.

In: American Journal of Applied Sciences, Vol. 5, No. 6, 2008, p. 714-720.

Research output: Contribution to journalArticle

@article{09420b65106141009a379891586da9e8,
title = "Isolated Malay digit recognition using pattern recognition fusion of dynamic time warping and hidden Markov models",
abstract = "This paper is presents a pattern recognition fusion method for isolated Malay digit recognition using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). The aim of the project is to increase the accuracy percentage of Malay speech recognition. This study proposes an algorithm for pattern recognition fusion of the recognition models. The endpoint detection, framing, normalization, Mel Frequency Cepstral Coefficient (MFCC) and vector quantization techniques are used to process speech samples to accomplish the recognition. Pattern recognition fusion method is then used to combine the results of DTW and HMM which uses weight mean vectors. The algorithm is tested on speech samples that are a part of a Malay corpus. This paper has shown that the fusion technique can be used to fuse the pattern recognition outputs of DTW and HMM. Furthermore it also introduced refinement normalization by using weight mean vector to get better performance with accuracy of 94{\%} on pattern recognition fusion HMM and DTW. Unlikely accuracy for DTW and HMM, which is 80.5{\%} and 90.7{\%} respectively.",
keywords = "Distance measurements and weight mean, Endpoint detection, Mel frequency cepstral coefficient, Vector quantization",
author = "Al-Haddad, {Syed Abdul Rahman} and {Abdul Samad}, Salina and Aini Hussain and Ishak, {Khairul Anuar}",
year = "2008",
language = "English",
volume = "5",
pages = "714--720",
journal = "American Journal of Applied Sciences",
issn = "1546-9239",
publisher = "Science Publications",
number = "6",

}

TY - JOUR

T1 - Isolated Malay digit recognition using pattern recognition fusion of dynamic time warping and hidden Markov models

AU - Al-Haddad, Syed Abdul Rahman

AU - Abdul Samad, Salina

AU - Hussain, Aini

AU - Ishak, Khairul Anuar

PY - 2008

Y1 - 2008

N2 - This paper is presents a pattern recognition fusion method for isolated Malay digit recognition using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). The aim of the project is to increase the accuracy percentage of Malay speech recognition. This study proposes an algorithm for pattern recognition fusion of the recognition models. The endpoint detection, framing, normalization, Mel Frequency Cepstral Coefficient (MFCC) and vector quantization techniques are used to process speech samples to accomplish the recognition. Pattern recognition fusion method is then used to combine the results of DTW and HMM which uses weight mean vectors. The algorithm is tested on speech samples that are a part of a Malay corpus. This paper has shown that the fusion technique can be used to fuse the pattern recognition outputs of DTW and HMM. Furthermore it also introduced refinement normalization by using weight mean vector to get better performance with accuracy of 94% on pattern recognition fusion HMM and DTW. Unlikely accuracy for DTW and HMM, which is 80.5% and 90.7% respectively.

AB - This paper is presents a pattern recognition fusion method for isolated Malay digit recognition using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). The aim of the project is to increase the accuracy percentage of Malay speech recognition. This study proposes an algorithm for pattern recognition fusion of the recognition models. The endpoint detection, framing, normalization, Mel Frequency Cepstral Coefficient (MFCC) and vector quantization techniques are used to process speech samples to accomplish the recognition. Pattern recognition fusion method is then used to combine the results of DTW and HMM which uses weight mean vectors. The algorithm is tested on speech samples that are a part of a Malay corpus. This paper has shown that the fusion technique can be used to fuse the pattern recognition outputs of DTW and HMM. Furthermore it also introduced refinement normalization by using weight mean vector to get better performance with accuracy of 94% on pattern recognition fusion HMM and DTW. Unlikely accuracy for DTW and HMM, which is 80.5% and 90.7% respectively.

KW - Distance measurements and weight mean

KW - Endpoint detection

KW - Mel frequency cepstral coefficient

KW - Vector quantization

UR - http://www.scopus.com/inward/record.url?scp=38049132885&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38049132885&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:38049132885

VL - 5

SP - 714

EP - 720

JO - American Journal of Applied Sciences

JF - American Journal of Applied Sciences

SN - 1546-9239

IS - 6

ER -