Design and Development of Door Security System Using Multi-Lingual Speech Recognition Techniques for Malay, Tamil and Chinese Language

Ng, Yik Heng (2023) Design and Development of Door Security System Using Multi-Lingual Speech Recognition Techniques for Malay, Tamil and Chinese Language. Final Year Project (Bachelor), Tunku Abdul Rahman University College.

Text Full Text -Ng Yik Heng.pdf Restricted to Registered users only Download (4MB)

Abstract

Door security system has evolve in the past years, since door plays an important role on home security since people have to enter the house through the door. Therefore, the paper propose a door security system using multi-lingual speech recognition techniques for Chinese, Tamil and English language. Speech is used as a tool for speech recognition since it contains features that could be trained by neural network to distinguish every voice pattern for users to perform classification. There are several factors that affects the performance of voice recognition, namely the effects on background noises. This door security system that uses multi-lingual speech recognition techniques would classify the sound of the speaker by letting them voice out fruits in any commonly used language in Malaysia, and the door security system will perform classification in order to identify is the voice pattern one of the user in the database. In order to implement this multi-lingual speech recognition door secuirty system, MATLAB application is used for the development platform of this project. Besides, Mel-Frequency Cepstral Coefficient (MFCC) is used as the feature extraction technique, Convolutional Neural Network (CNN) is used as the training and matching of system while GOLDWAVE application is used as the recording of audio signal