Development of FPGA based Human Voice Recognition System with MFCC feature
Journal Title: INTERNATIONAL JOURNAL OF ENGINEERING TRENDS AND TECHNOLOGY - Year 2014, Vol 8, Issue 10
Abstract
The voice recognition development on the hardware is also a challenging field due to minimal hardware resource utilization with higher accuracy demand. This paper described the FPGA based human voice recognition system. This system includes voice activity detection, MFCC feature extraction, HMM filter generation and classification of voice. The system is train for different person with the repeated voice for achieving the higher accuracy. The HMM filter coefficient for different person is only stored for reducing the memory utilization. The standard FFT and DCT blocks are used to reduce the hardware utilization. The development results are given in this paper for illustrating the effectiveness of system.
Authors and Affiliations
Mr. Anand Mantri , Mr. Mukesh Tiwari , Mr. Jaikaran Singh
Keywords
Related Articles
- EP ID EP105018
- DOI -
- Views 104
- Downloads 0
An Improved Performance of Sensorless PMSM Drive Control with Sliding Mode Observer in Low Speed Operation
The aim of these paper is to realize a sensorless vector control scheme for a non-salient pole PMSM using a state observer of kind “Sliding Mode” for rotor flux position and speed estimation. The proposed scheme of...
A Comparative Study Of Impulse Noise Reduction In Digital Images For Classical And Fuzzy Filters
Efficient impulse noise removal is an important issue in image processing. It is caused error in the data communication generated in noisy sensors or communication channels or by error during the data capture from digita...
Automation in Clay and Thermal Industry Waste Products
Construction is a part of infrastructure, which is essential to promote growth in the economy. India is one of the fastest growing economies in the world. The scope of Infrastructure industry is enormous, as t...
Fingerprint Based Gender Classification Using 2D Discrete Wavelet Transforms and Principal Component Analysis
Fingerprint evidence is undoubtedly the most reliable and acceptable evidence till date in the court of law. Fingerprints are obtained at the site of crime and in many old monuments and in excavated things. Estimat...
Privacy and Utility in Data Publishing with Full Functional Dependencies
A number of methods have recently been proposed for privacy preserving data mining of multidimensional data records. One of the methods for privacy preserving data mining is that of anonymization, in which a reco...