Statistical band selection for descriptors of MBSE and MFCC-based features for accent classification of Malaysian English / Yusnita M. A. ...[et al.]

M. A., Yusnita and M. P., Paulraj and Yaacob, Sazali and A. B., Shahriman and Mokhtar, Nor Fadzilah (2013) Statistical band selection for descriptors of MBSE and MFCC-based features for accent classification of Malaysian English / Yusnita M. A. ...[et al.]. Journal of Electrical and Electronic Systems Research (JEESR), 6: 4. pp. 33-48. ISSN 1985-5389

Abstract

Accent is a major cause of speech variability that complicates the speech technology systems. Interestingly, ethnicity is one of the influential factor that give rise to accentuation in speech. Proper approach of extracting ethnical accent information is utmost crucial in many speech applications. This paper proposes an efficient way of analyzing the ethnical accent using statistical knowledge of log-energies of fourier transformed derived mel-filter banks. A simple algorithm to select bands so called statistical band selection (SBS) method using smallest variances within class scores was developed to optimize the presentation of
speech features. The experiments were conducted on selective accent-sensitive words of male and female speakers originate from three major ethnics in Malaysia. Firstly, statistical descriptors such as mean, standard deviation, kurtosis and the ratio of standard deviation to kurtosis of mel-bands spectral energy and secondly, mel-frequency cepstral coefficients were extracted from the selected bands to model an accent classifier, implemented based on neural network model and K-nearest neighbors. Experimental results showed that SBS has increased the performance of accent classification system by achieving better accuracy rates between 4% to 6%, lesser memory requirement between 22% to 55% and faster speed of 70% on average of three-class accent problem.

Metadata

Item Type: Article
Creators:
Creators
Email / ID Num.
M. A., Yusnita
yusnita082@ppinang.uitm.edu.my
M. P., Paulraj
paul@unimap.edu.my
Yaacob, Sazali
s.yaacob@unimap.edu.my
A. B., Shahriman
shahriman@unimap.edu.my
Mokhtar, Nor Fadzilah
norfadzilah105@ppinang.uitm.edu.my
Subjects: P Language and Literature > PE English language > Malaysia
Divisions: Universiti Teknologi MARA, Pulau Pinang > Permatang Pauh Campus > Faculty of Electrical Engineering
Journal or Publication Title: Journal of Electrical and Electronic Systems Research (JEESR)
UiTM Journal Collections: UiTM Journal > Journal of Electrical and Electronic Systems Research (JEESR)
ISSN: 1985-5389
Volume: 6
Page Range: pp. 33-48
Keywords: Statistical band selection, Melbands spectral energy, Mel-frequency cepstral coefficients, Accent classification, Artificial neural network, K-nearest neighbors, Malaysian English
Date: June 2013
URI: https://ir.uitm.edu.my/id/eprint/62950
Edit Item
Edit Item

Download

[thumbnail of 62950.pdf] Text
62950.pdf

Download (1MB)

ID Number

62950

Indexing

Statistic

Statistic details