東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

A Speaker Verification System for Ar...

King Fahd University of Petroleum and Minerals (Saudi Arabia).

Linked to FindBook

Google Book

Amazon

博客來

A Speaker Verification System for Arabic.

Record Type:	Electronic resources : Monograph/item
Title/Author:	A Speaker Verification System for Arabic./
Author:	Al-Telmisani, Essam Abed.
Description:	99 p.
Notes:	Source: Masters Abstracts International, Volume: 46-04, page: 2302.
Contained By:	Masters Abstracts International46-04.
Subject:	Engineering, System Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1451854
ISBN:	9780549449171

A Speaker Verification System for Arabic.
Al-Telmisani, Essam Abed.

A Speaker Verification System for Arabic. - 99 p.

Source: Masters Abstracts International, Volume: 46-04, page: 2302.

Thesis (M.S.)--King Fahd University of Petroleum and Minerals (Saudi Arabia), 2008.

In this thesis a new Speaker Verification System (SVS) methodology is developed. The objective is to develop a SVS system that achieves high identification accuracy with low storage requirements for the use in smart card-based systems.

ISBN: 9780549449171Subjects--Topical Terms:

1018128
Engineering, System Science.

A Speaker Verification System for Arabic.
LDR:01809nmm 2200253 a 45 001 867533
005 20100804
008 100804s2008 ||||||||||||||||| ||eng d
020 $a 9780549449171
035 $a (UMI)AAI1451854
035 $a AAI1451854
040 $a UMI $c UMI
100 1 $a Al-Telmisani, Essam Abed. $3 1036273
245 1 2 $a A Speaker Verification System for Arabic.
300 $a 99 p.
500 $a Source: Masters Abstracts International, Volume: 46-04, page: 2302.
502 $a Thesis (M.S.)--King Fahd University of Petroleum and Minerals (Saudi Arabia), 2008.
520 $a In this thesis a new Speaker Verification System (SVS) methodology is developed. The objective is to develop a SVS system that achieves high identification accuracy with low storage requirements for the use in smart card-based systems.
520 $a This proposed system combines the advantages of the simple structure of text-dependent systems and the performance of text-independent systems. The feature extraction utilized the Mel-Frequency Cepstrum Coefficients MFCC for its superior performance, and user template is based on a Vector Quantization codebook for fast and efficient pattern classification. A new adaptive threshold is also proposed to achieve improved performance with time and to mitigate temporarily changes in speaker voice. The system is trained and tuned for Arabic speakers using initially certain parts front the holy Qura'an. A sample of eighteen Arabic speakers is used to evaluate the system performance. The system achieves an accuracy of 0.01 for the False Acceptance Rate (FAR), and 0.04 for the False Rejection Rate (FRR).
590 $a School code: 1088.
650 4 $a Engineering, System Science. $3 1018128
690 $a 0790
710 2 $a King Fahd University of Petroleum and Minerals (Saudi Arabia). $3 1030607
773 0 $t Masters Abstracts International $g 46-04.
790 $a 1088
791 $a M.S.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1451854