Person Authentication by voice and image using ANFIS and Shifted MFCC

Abstract

In security systems, the interest in using biometric technologies for person authentication has grown rapidly. Voice is one of the most promising and mature biometric modalities for secured access control. Here presents a novel approach to recognize/identify speakers with their images by including a new set of features and using Gaussian mixture models (GMMs). In this research, the concept of shifted MFCC is introduced so as to incorporate accent information in the recognition algorithm. VQ method is used for feature matching due to the ease of implementation and high accuracy. The goal of this project is to build a simple, yet complete and representative automatic speaker recognition system. Due to the limited space, we will only test our system on a very small speech database. The image of the speaker will also be displayed for further clarification. We can also hear the spelled word of each speaker in background while running the program. The algorithm showed improvements over the performance of the previous works.

Authors and Affiliations

Bhavyadas, Murugantham C, H S DivakaraMurthy, Parameshachari B D

Keywords

Related Articles

An improved contourlet transform technique for image watermarking

In this paper, contourlet transform technique is explored to hide the information confidentially from the unauthorized users. The image is decomposed into subbands by using contourlet transform. These subbands are us...

Pilot-Symbol Assisted Power Delay Profile Estimation for MIMO-OFDM Systems

In this paper a power delay profile (PDP) estimation technique is proposed for the linear minimum mean square error (LMMSE) channel estimator of multipleinput multiple-output orthogonal frequency division multiplexing...

Characterization of Accelerometer for Defense Application

The speed of the motor is typically measured in RPM (revolutions per minute). This can be obtained in many ways. A strobe light (stroboscope) is one of the apparatuses to quantify RPM. Another strategy can utilize op...

Resource Provisioning Techniques in Cloud Computing Environment: A Survey

Cloud Computing is a model for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, applications and services) that can be rapidly provisioned a...

Implementation of MIMO Technique in Vehicular Adhoc Network for Different Mobility Patterns

VANETs (Vehicular ad-hoc network) is a special type if intelligent system used for road safety which is characterized by a very dynamic topology with partial infrastructure support, patterned mobility, and mobile nod...

Download PDF file
  • EP ID EP27618
  • DOI -
  • Views 330
  • Downloads 4

How To Cite

Bhavyadas, Murugantham C, H S DivakaraMurthy, Parameshachari B D (2013). Person Authentication by voice and image using ANFIS and Shifted MFCC. International Journal of Research in Computer and Communication Technology, 2(8), -. https://europub.co.uk/articles/-A-27618