A Review of Mel Frequency Cepstral Coefficient (MFCC) Analysis of Speech and Neural Network |
Author(s): |
| Md Ibrahim Khalil , Nanjing University of Science and Technology |
Keywords: |
| MFCC, Neural Network |
Abstract |
|
Human voice is the most natural and easiest way of communication with each other. But communication with a machine is not a simple task to do. After lots of hard works people have been developed computer to communicate with machine. Automatic speech recognition permitting a natural and simple to use method of communication between human and machine is an active area of research. Mel Frequency Cepstral Coefficient (MFCCs) are the most prominent and commonly used features in most of the speaker and speech recognition applications. Recently, another acoustic model based on deep neural networks (DNN) has been presented. This paper gives a review of MFCCs improvement techniques that are applied in the speech recognition system. Here also discussed neural networks. |
Other Details |
|
Paper ID: IJSRDV7I10095 Published in: Volume : 7, Issue : 1 Publication Date: 01/04/2019 Page(s): 1892-1895 |
Article Preview |
|
|
|
|
