A Speech Recognition System for Urdu Language

Azam Beg; S. K. Hasnain

A Speech Recognition System for Urdu Language

Azam Beg, S. K. Hasnain

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper investigates use of a machine learnt model for recognition of individually words spoken in Urdu language. Speech samples from many different speakers were utilized for modeling. Original time-domain samples are normalized and pre-processed by applying discrete Fourier transformation for speech feature extraction. In frequency domain, high degree of correlation was found for the same words spoken by different speakers. This helped produce models with high recognition accuracy. Details of model realization in MATLAB are included in this paper. Current work is being extended using linear predictive coding for efficient hardware implementation.

Original language	English
Title of host publication	Communications in Computer and Information Science
Editors	D.M. Akbar Hussain, Abdul Qadeer Khan Rajput, Bhawani Shankar Chowdhry, Quintin Gee
Pages	118-126
Number of pages	9
Publication status	Published - 2009

Publication series

Name	Communications in Computer and Information Science
Volume	20
ISSN (Print)	1865-0929

Keywords

Data pre-processing
Feature extraction
Machine learning
Modeling
Speaker independent system
Urdu speech processing

ASJC Scopus subject areas

General Computer Science
General Mathematics

Cite this

A Speech Recognition System for Urdu Language. / Beg, Azam; Hasnain, S. K.
Communications in Computer and Information Science. ed. / D.M. Akbar Hussain; Abdul Qadeer Khan Rajput; Bhawani Shankar Chowdhry; Quintin Gee. 2009. p. 118-126 (Communications in Computer and Information Science; Vol. 20).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

@inproceedings{6e3af61007484a8989844e71f8bd0007,

title = "A Speech Recognition System for Urdu Language",

abstract = "This paper investigates use of a machine learnt model for recognition of individually words spoken in Urdu language. Speech samples from many different speakers were utilized for modeling. Original time-domain samples are normalized and pre-processed by applying discrete Fourier transformation for speech feature extraction. In frequency domain, high degree of correlation was found for the same words spoken by different speakers. This helped produce models with high recognition accuracy. Details of model realization in MATLAB are included in this paper. Current work is being extended using linear predictive coding for efficient hardware implementation.",

keywords = "Data pre-processing, Feature extraction, Machine learning, Modeling, Speaker independent system, Urdu speech processing",

author = "Azam Beg and Hasnain, {S. K.}",

year = "2009",

language = "English",

isbn = "9783540898528",

series = "Communications in Computer and Information Science",

pages = "118--126",

editor = "{Akbar Hussain}, D.M. and Rajput, {Abdul Qadeer Khan} and Chowdhry, {Bhawani Shankar} and Quintin Gee",

booktitle = "Communications in Computer and Information Science",

}

TY - GEN

T1 - A Speech Recognition System for Urdu Language

AU - Beg, Azam

AU - Hasnain, S. K.

PY - 2009

Y1 - 2009

N2 - This paper investigates use of a machine learnt model for recognition of individually words spoken in Urdu language. Speech samples from many different speakers were utilized for modeling. Original time-domain samples are normalized and pre-processed by applying discrete Fourier transformation for speech feature extraction. In frequency domain, high degree of correlation was found for the same words spoken by different speakers. This helped produce models with high recognition accuracy. Details of model realization in MATLAB are included in this paper. Current work is being extended using linear predictive coding for efficient hardware implementation.

AB - This paper investigates use of a machine learnt model for recognition of individually words spoken in Urdu language. Speech samples from many different speakers were utilized for modeling. Original time-domain samples are normalized and pre-processed by applying discrete Fourier transformation for speech feature extraction. In frequency domain, high degree of correlation was found for the same words spoken by different speakers. This helped produce models with high recognition accuracy. Details of model realization in MATLAB are included in this paper. Current work is being extended using linear predictive coding for efficient hardware implementation.

KW - Data pre-processing

KW - Feature extraction

KW - Machine learning

KW - Modeling

KW - Speaker independent system

KW - Urdu speech processing

UR - http://www.scopus.com/inward/record.url?scp=78649854738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649854738&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78649854738

SN - 9783540898528

T3 - Communications in Computer and Information Science

SP - 118

EP - 126

BT - Communications in Computer and Information Science

A2 - Akbar Hussain, D.M.

A2 - Rajput, Abdul Qadeer Khan

A2 - Chowdhry, Bhawani Shankar

A2 - Gee, Quintin

ER -

A Speech Recognition System for Urdu Language

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this