Welcome to python_speech_features’s documentation!

This library provides common speech features for ASR including MFCCs and filterbank energies. If you are not sure what MFCCs are, and would like to know more have a look at this MFCC tutorial: http://www.practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/.

You will need numpy and scipy to run these files. The code for this project is available at https://github.com/jameslyons/python_speech_features .

Supported features:

  • features.mfcc() - Mel Frequency Cepstral Coefficients
  • features.fbank() - Filterbank Energies
  • features.logfbank() - Log Filterbank Energies
  • features.ssc() - Spectral Subband Centroids

To use MFCC features:

from features import mfcc
from features import logfbank
import scipy.io.wavfile as wav

(rate,sig) = wav.read("file.wav")
mfcc_feat = mfcc(sig,rate)
fbank_feat = logfbank(sig,rate)


From here you can write the features to a file etc.

Functions provided in features module

Functions provided in sigproc module

Indices and tables