Speaker Independent Robust Speech Recognition Using Wavelet Transform and Neural Network

  • Irshad,ZainulAbdin Jaffery,Khwaja M Rafi, Shaheen Khan, Nadeem Ahmad

Abstract

For smooth interaction between humans and machines, speech recognition can play a big role in future.In this paper, a Speaker Independent Speech Recognition system is designed with the help of Artificial Neural Network.Wavelet transform is used to extract the features from the speech samples. These features were used to train a  10 layer, 7 input feed-forward neural network to classify the speech samples. Samples were recorded from 10 different persons using a mobile phone for different speech words. Advantages of Wavelet transform and Neural Network over conventional HMMs are combined to design a Speaker Independent Speech Recognition system. An accuracy of more than 99% was achieved in word recognition using multilayer feedforward Neural Network.

Published
2020-06-01
How to Cite
Irshad,ZainulAbdin Jaffery,Khwaja M Rafi, Shaheen Khan, Nadeem Ahmad. (2020). Speaker Independent Robust Speech Recognition Using Wavelet Transform and Neural Network . International Journal of Advanced Science and Technology, 29(7s), 5871-5877. Retrieved from https://sersc.org/journals/index.php/IJAST/article/view/26506