Speech Recognition Interactive System for Vehicle

 




 

Loh, Chee Yang (2017) Speech Recognition Interactive System for Vehicle. Final Year Project (Bachelor), Tunku Abdul Rahman University College.

[img] Text
Loh Chee Yang.pdf
Restricted to Registered users only

Download (3MB)

Abstract

Technology that enables a computer system to capture the words or sentences spoken by a human with the help of microphone is called Speech Recognition. In order to enable the system to recognize all the words or sentences uttered by a human, a Speech Recognition Engine is needed to perform the task. Practically, there are number of factors that may influence the performance of the Speech Recognition Engine such as the vocabularies used by the human, multiple users and noisy environment. This project aims to develop a speech recognition interactive system for the vehicles. In this project, MFCC algorithm has been used as the feature extraction techniques while Vector Quantization techniques have been used to segment the speeches. To implement these algorithms, MATLAB has been used as the development platform. 16 commands have been recorded to control various functions in a vehicle. The tests have been performed under quiet and noisy environment. The accuracy is 100% for quiet environment and 93.75% for noisy environment. Nowadays, the Speech Recognition System has been implemented in the field of automotive to control the features in cars such as controlling the multimedia system by using command and output will be generated in order to respond to the user. From the perspective of current technology, there is a long history with several waves of major innovations for Speech Recognition due to this field has benefited from advances in big data and deep learning recently. Actually the advancement of this technology is not only by the surge of academic papers published in the field while world-wide industry has adopted of a variety of deep learning methods in deploying and designing the Speech Recognition System such as Google, Microsoft, IBM and Hewlett Packard (Formally known as HP).

Item Type: Final Year Project
Subjects: Technology > Electrical engineering. Electronics engineering
Faculties: Faculty of Engineering and Built Environment > Bachelor of Engineering (Honours) Electrical and Electronics
Depositing User: Library Staff
Date Deposited: 22 Oct 2019 01:39
Last Modified: 18 Apr 2022 08:57
URI: https://eprints.tarc.edu.my/id/eprint/10813