Intelligent automatic starting engine based on voice recognition system

Abstract

A vehicle key provides the main functions for accessing the vehicle, accessing the ignition mechanism, and the ability to actually start the car. Voice based starting engine access control system potentially replaces these main functions by replacing the key with the specific user voice. In the proposed system, the access may be authorized simply by means of an enrolled user speaking into a microphone attached to the system. The proposed system then will decide whether the word is `On' or `Off'. The decision voice will be sent to Arduino in order to activate the automotive relay, which will be used to activate the engine's motor starter. Furthermore, the intelligent system approach is used to develop authorized words model based on the voice. Particularly Support Vector Machines based classification system is used in the proposed system to identify the authorized words. Experimental results confirm the effectiveness of the proposed intelligent Automatic voice-based starting engine access control system based on Mel-Frequency Ceptral Coefficient (MFCC) and Support Vector Machines (SVMs), since it resulting the training and testing accuracy of 100% and 92.15%, respectively.