SPEECH RECOGNITION USING HMM/ANN HYBRID MODEL FOR TREASURE SECURITY
Author(s):
NITESH PATEL, MAYUR HELKAR, DATTATRAY BADE, YAMINI SAVKHEDKAR
Keywords:
ARM 7, Buzzer, LCD Display, Matlab 2013a, Solenoid, Treasure Box
Abstract
-Speech recognition is an important component of biological identification which is an integrated technology of acoustics, signal processing and artificial intelligence. The goal in hybrid systems for ASR is to take advantage from the properties of both HMM and ANNs, improving flexibility and ASR performance So we have used together effects of ANN/HMM in our project so that limitations of both can be effectively removed in our project. The hybrid HMM/ANN is able to combine the strength of HMM in sequential modelling structure and ANN in pattern classification. Thus purpose of speech in our project is to get rid of the Old methods of locking systems which require keys and other method like scrolling 4-digits of password. Thus use of this hybrid model in Treasure Security is useful for locking purpose where the kit is trained within voice samples of the one or more users and used as password for the system. The system will authenticate the user whose voice will be matched with the entire data within the stored values and if authentication is done the system will open the treasure and if false condition appears it will remain closed.
Article Details
Unique Paper ID: 144559

Publication Volume & Issue: Volume 4, Issue 1

Page(s): 1 - 3
Article Preview & Download




Go To Issue



Call For Paper

Volume 4 Issue 5

Last Date 25 October 2017


About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Contact Details

Telephone:704 821 9842/43
Email: editor@ijirt.org
Website: ijirt.org