Performance Analysis of MLP, Modified ERNN and TDNN on Telugu Command Recognition

Abstract

In this paper, Telugu speech recognition is implemented using MLP and dynamic neural networks in MATLAB. Ten Telugu commands are the words of interest for recognition. Speech samples are collected for ten Telugu words from 30 different speakers in a noise free environment. Front end processing and LPC feature extraction are applied to raw speech data. Data is divided into training and testing sets. This paper gives different topologies of Artificial Neural Networks are used to investigate the Automated Speech Recognition of Telugu speech. The neural network topologies considered are MLP, Modified ERNN and TDNN. The word models are created by giving training data set as inputs to these networks and trained using backpropagation algorithm. Each neural network is trained to identify and classify the words into the respective word models. The testing data set is used to analyze the performance of the network.