scholarly journals Design of discriminant functions for distortion sequences in dynamic pattern matching for speech recognition

1990 ◽  
Vol 88 (S1) ◽  
pp. S102-S102
Author(s):  
Pao‐Chung Chang ◽  
Biing‐Hwang Juang

Automatic speech recognition has attained a lot of significance as it can act as easy communication link between machines and humans. This mode of communication is easy for man to use as it is effortless and easy. Many approaches for extraction of the features of the speech and classification of speech have been considered. This paper unveils the importance of neutral network and the way it can be used for recognition of speech. Mel Frequency Cepstrum Coefficients is made use of for extraction of the features from the voice. For pattern matching neural network has been used. MATLAB has been used to show how the speech is recognized. In this paper the speech recognition has been done firstly by multilayer feed forward neural network using Back propagation algorithm. Then the process of speech recognition is shown by using Radial basis function neural network. The paper then analyzes the performance of both the algorithms and experimental result shows that BPNN outperforms the RBFNN.


Author(s):  
Tobias Kohn ◽  
Guido van Rossum ◽  
Gary Brandt Bucher II ◽  
Talin ◽  
Ivan Levkivskyi

1964 ◽  
Vol 36 (5) ◽  
pp. 1031-1031
Author(s):  
S. J. Campanella ◽  
D. C. Coulter ◽  
P. Engler

Sign in / Sign up

Export Citation Format

Share Document