Implementation Of Back-Propagation Neural Network For Isolated Bangla Speech Recognition

TL;DR

This paper develops a back-propagation neural network system for recognizing isolated Bangla speech digits, achieving high accuracy for both known and unknown speakers using MFCC features.

Contribution

It presents a novel application of back-propagation neural networks for Bangla digit speech recognition with promising accuracy results.

Findings

Recognition rate of 96.33% for known speakers

Recognition rate of 92% for unknown speakers

Effective use of MFCC features for speech recognition

Abstract

This paper is concerned with the development of Back-propagation Neural Network for Bangla Speech Recognition. In this paper, ten bangla digits were recorded from ten speakers and have been recognized. The features of these speech digits were extracted by the method of Mel Frequency Cepstral Coefficient (MFCC) analysis. The mfcc features of five speakers were used to train the network with Back propagation algorithm. The mfcc features of ten bangla digit speeches, from 0 to 9, of another five speakers were used to test the system. All the methods and algorithms used in this research were implemented using the features of Turbo C and C++ languages. From our investigation it is seen that the developed system can successfully encode and analyze the mfcc features of the speech signal to recognition. The developed system achieved recognition rate about 96.332% for known speakers (i.e., speaker dependent) and 92% for unknown speakers (i.e., speaker independent).