MFCC Feature Extraction
2016-08-23
3 0 0
no vote
Other
Earn points
Implementation of MFCC feature extraction: to do this take a speech signal and divide the signal in frames then each frame is passed through the different blocks. The first block is the pre emphasis which boost the signal and it should be passed through the windowing to analyse single frame then the signal fft has to be calculated then this signal is passed through the mel filter bank which generally generates 39 coefficient in this code and these 39 coefficients are passed through the logarithm and finally calculate the inverse DCT to generate the 13 coefficients. these 13 coefficients are converted to 39 by taking the residuals which are nothing but the delta feature and double delta feature.
matlab
mfcc
提取
特征
Related Source Codes
GMSK Linear Receiver
0
0
no vote
NSGA-II algorithm
0
0
no vote
NSGA-III multi-objective optimization algorithm
0
0
no vote
Compressed sensing example
0
0
no vote
CFAR detector example
0
0
no vote
No comment