The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SYSTEMS AND CONTROL
Transactions ID Number: 52-642
Full Name: Sumithra Palanisamy
Position: Professor
Age: ON
Sex: Female
Address: Professor, Department of ECE,Bannari Amman Institute of Technology,Sathyamnagalam,Erode,TamilNadu
Country: INDIA
Tel: 226183
Tel prefix: 91 4295
Fax: 226666
E-mail address: mgsumithra@rediffmail.com
Other E-mails: jeniraj24@gmail.com, mgsumithra@yahoo.co.in
Title of the Paper: A New Speaker Recognition System with Combined Feature Extraction Techniques
Authors as they appear in the Paper: Sumithra M G Thanuskodi K Helen jenifer archana A
Email addresses of all the authors: mgsumithra@rediffmail.com,thanush_dr@rediffmail.com,jeniraj24@gmail.com
Number of paper pages: 11
Abstract: Text-independent automatic speaker recognition has been an active research subject for many years due to its potential for applications in many domains. A more flexible speaker recognition system is able to operate without explicit user cooperation and independent of the spoken utterance (called text-independent mode) is needed. This paper focuses on the text-independent speaker recognition system. Analysis was made over different existing feature extraction techniques and speaker modeling techniques. Based on the analysis a new speaker recognition scheme was proposed. The proposed scheme uses the MFCC feature extraction method for identification and MMFCC features for verification. For modeling LBG algorithm was used. The performance was evaluated against 1000 speakers for 10 different languages with duration of 10 sec for training the system and for testing 5 sec duration samples were used. Experimental results of the proposed system showed that higher recognitio!
n accuracy of 93% is achieved by increasing the number of filter banks used for feature extraction method, more competitive with existing system using vector quantization with lesser computational complexity.
Keywords: Feature extraction, Speaker modeling, Vector quantization, False acceptance, False rejection
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: Speech Processing, Automatic Speaker Recognition
IP ADDRESS: 202.129.196.83
