# mfcc

Compute MFCC features from an audio signal.

#### Return

An array of size (NUMFRAMES by numcep) containing features. Each row holds 1 feature vector.

## Parameters

the audio signal from which to compute features. Should be an N*1 array

the samplerate of the signal we are working with.

the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)

the step between successive windows in seconds. Default is 0.01s (10 milliseconds)

the number of cepstrum to return, default 13

the number of filters in the filterbank, default 26.

the FFT size. Default is 512.

lowest band edge of mel filters. In Hz, default is 0.

highest band edge of mel filters. In Hz, default is samplerate/2

apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97.

apply a lifter to final cepstral coefficients. 0 is no lifter. Default is 22.

if this is true, the zeroth cepstral coefficient is replaced with the log of the total frame energy.

the analysis window to apply to each frame. By default no window is applied.