# Generating codebook with MFCC feature extraction

Status
Not open for further replies.

#### Biruntha

##### Junior Member level 1
In signal processing, i did feature extraction using MFCC. then use kmeans(k=6) clustering technique to generate the code-book.so i got 6 rows for each frame of data. but while testing i got 20 rows for each frame of data. because In Mel Frequency Warping, the number of mel cepstral coefficients,K,is typically chosen as 20. so i got 20 rows. After that how can i calculate the Euclidean distance? anyone help?

while training phase i got,
Code:
       F1     F2       F3      F4      F5
X1    -17.003 -17.892 -18.661 -17.440 -16.521
X2    -1.127  -2.341  -3.255  -1.546  -0.222
X3    -6.772  -7.727  -8.329  -7.095  -6.293
X4     1.103   0.343   0.166   0.941   1.369
X5     0.263  -0.176   0.124   0.457   0.478
X6     0.177  -0.105   0.407   0.316   -0.035
like this i got 20 rows while testing phase.

Status
Not open for further replies.