Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.
There are 22words.Each word has 150 samples. So I have a total of 3300 samples. 75% for train , 25% for test.The features acoustic vectors are MFCC coefficients. I use MFCC as the input of DBN.But the 22 words can only be divided into one class. I don't konw the reason .Can you help me
Dallas0608
commented
6 years ago
There are 22words.Each word has 150 samples. So I have a total of 3300 samples. 75% for train , 25% for test.The features acoustic vectors are MFCC coefficients. I use MFCC as the input of DBN.But the 22 words can only be divided into one class. I don't konw the reason .Can you help me