SPEAKER RECOGNITION AND AUTHENTICATION?
Journal: International Journal of Computer Science and Mobile Computing - IJCSMC (Vol.2, No. 5)Publication Date: 2013-05-15
Authors : Rakesh D R JAYASIMHAN N K;
Page : 402-407
Keywords : Cepstral analysis; Delta Coefficients; real-time processing; Dynamic Time Warping;
Abstract
In today’s society, highly accurate personal identification systems are required. Passwords or pin numbers can be forgotten or forged and are no longer considered to offer a high level of security. The use of biological features, biometrics, is becoming widely accepted as the next level for security systems. Speaker Recognition and Authentication is a method of identifying persons from their voice. Speaker-specific characteristics exist in speech signals due to different speakers having different resonances of the vocal tract; these features are extracted from the voice of the speaker and used for the recognition of individual speaker. In this paper we present a real-time text dependent speaker recognition and authentication system which serve as intermediary step towards the implementation as an embedded system. Process is based on computing the Mel Frequency Cepstral Coefficients and the derived Dynamic Coefficients, while classifying features using a Dynamic Time Warping approach.
Other Latest Articles
- A STUDY OF PRIVACY-PRESERVING WHILE SHARING SENSITIVE INFORMATION?
- An Efficient Back Propagation Neural Network Based Face Recognition System Using Haar Wavelet Transform and PCA?
- An Efficient Pixel-shuffling Based Approach to Simultaneously Perform Image Compression, Encryption and Steganography?
- An Overview on Reactive Protocols for Mobile Ad-Hoc Networks?
- ROUTING ATTACKS IN MOBILE AD HOC NETWORKS?
Last modified: 2013-05-31 01:02:57