The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMMUNICATIONS
Transactions ID Number: 32-555
Full Name: Abdel-Rahman Al-Qawasmi
Position: Assistant Professor
Age: ON
Sex: Male
Address: P.O. box 1 Philadelphia University 19392 Jordan
Country: JORDAN
Tel: 962777420872
Tel prefix: 962777420872
Fax:
E-mail address: qawasmi@philadelphia.edu.jo
Other E-mails: telecomjo@yahoo.com
Title of the Paper: Speaker Identification System-based Mel Frequency and Wavelet Transform using Neural Network Classifier
Authors as they appear in the Paper: Wael Al-Sawalmeh . Khaled Daqrouq. Omar Daoud. Abdel-Rahman Al-Qawasmi
Email addresses of all the authors: narin912007@yahoo.com, haleddaq@yahoo.com, odaoud@philadelphia.edu.jo,qawasmi@philadelphia.edu.jo
Number of paper pages: 10
Abstract: In order to improve the robustness to noise in speaker identification systems, the Mel Frequency Cepstral Coefficients (MFCC) and Continuous Wavelet Transform (CWT) are used in this work through features tracking. To extract the essential speaker features, in this paper, two methods are used to investigate the identification accuracy in non-stationary signals; CWT and MFCC. For the purpose of classifying these features Feed Forward Back Propagation Neural Network (FFBNN) is imposed, since it gives better classification accuracy over statistical methods in the literature. A simulation program has been built to check the efficiency of the proposed work; at certain level of CWT (as an example 6dB) the achieved classification was approximately 99.7%.
Keywords: Speaker identification; Continuous wavelet transform; Cepstral coefficients; and Neural network
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: qawasmi@philadelphia.edu.jo
IP ADDRESS: 194.165.157.174
