Voice Command Recognition System Based on MFCC and VQ Algorithms

Authors: Mahdi Shaneh, Azizollah Taheri

Abstract:

The goal of this project is to design a system to recognition voice commands. Most of voice recognition systems contain two main modules as follow “feature extraction" and “feature matching". In this project, MFCC algorithm is used to simulate feature extraction module. Using this algorithm, the cepstral coefficients are calculated on mel frequency scale. VQ (vector quantization) method will be used for reduction of amount of data to decrease computation time. In the feature matching stage Euclidean distance is applied as similarity criterion. Because of high accuracy of used algorithms, the accuracy of this voice command system is high. Using these algorithms, by at least 5 times repetition for each command, in a single training session, and then twice in each testing session zero error rate in recognition of commands is achieved.

Keywords: MFCC, Vector quantization, Vocal tract, Voicecommand.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1060187

References:

[1] Deller J.R. Hansen, J.H.L &.Proakis J.G., (1993), Discrete-Time Processing of Speech Signal, New York, Macmillan Publishing Company .
[2] Rabiner, L. R. and Juang, B.-H. (1993), Fundamentals of Speech Recognition, Prentice-Hall, Englewood Cli_s, NJ.
[3] Winther J├©rgensen and Lasse Lohilahti M├©lgaard, IMM-THESIS-2006, Tools for Automatic Audio Indexing
[4] Christian Spanner 2005, Speech codec identification for Error Correction of Across-Channel effects in speech coded environments
[5] B. Richard, january, 2001, "Text-independent speaker recognition using source based features", Master of philosophy, Wildermoth Griffith University Australia
[6] Tejaswini Hebalkar, Spring 2000 Voice Recognition and Identification System Final Report 18-551 Digital Communications and Signal Processing Systems Design
[7] Nilsson Magnus, October 2001, Speaker Verification in JAVA, A thesis submitted in partial fulfillment of the requirements for the degree of Master of Computer and Information Engineering, School of Microelectronic Engineering, Griffith University.