Enhance Cepstrum-Based (MFCC) Extraction Technique With Wavelet Coefficient Method For Improving Identification Accuracy

Draman@Muda, Noor Azilah and Muda, Azah Kamilah and Choo, Yun Huoy and Ahmad, Sabrina and Shahrir, Mohammad Shazri (2017) Enhance Cepstrum-Based (MFCC) Extraction Technique With Wavelet Coefficient Method For Improving Identification Accuracy. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Text Enhance Cepstrum-Based (MFCC) Extraction Technique With Wavelet Coefficient Method For Improving Identification Accuracy.pdf - Submitted Version Restricted to Registered users only Download (143kB)

Abstract

Various methods of biometric identification for authentication purposes are introduced and using human voice for human identity as one of the methods is gaining interest from researchers.The human voice contains an anatomical structure that is unique for every person. This quality of information allows possible identification,especially for security intention.During identification,the analysis should only concentrate on the human voice,however,besides the voice signal, background sound which is termed the noise should also be considered.As the noise does not contribute to the identification, it should be eliminated.This research focuses on integrating MFCC feature extraction method with a wavelet-based coefficient method to extract the human anatomical structure of features and eliminate the noise concurrently.The Mel frequency cepstral coefficient (MFCC) is used to represent the unique anatomical structure of the human voice.The enhanced technique is expected to increase the accuracy of the identification process while at the same time reduce the processing time.The increment of accuracy in the identification process is hoped to benefit the security alertness.

Actions (login required)

View Item