python_speech_features

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 thisMFCC tutorial

Project Documentation

Installation

This project is on pypi

To install from pypi:

pip install python_speech_features

From this repository:

git clone https://github.com/jameslyons/python_speech_features
python setup.py develop

Usage

Supported features:

• Mel Frequency Cepstral Coefficients

• Filterbank Energies

• Log Filterbank Energies

• Spectral Subband Centroids

Example use

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

MFCC Features

The default parameters should work fairly well for most cases, if you want to change the MFCC parameters, the following parameters are supported:

python
def mfcc(signal,samplerate=16000,winlen=0.025,winstep=0.01,numcep=13,
                 nfilt=26,nfft=512,lowfreq=0,highfreq=None,preemph=0.97,
     ceplifter=22,appendEnergy=True)

Filterbank Features

These filters are raw filterbank energies. For most applications you will want the logarithm of these features. The default parameters should work fairly well for most cases. If you want to change the fbank parameters, the following parameters are supported:

python
def fbank(signal,samplerate=16000,winlen=0.025,winstep=0.01,
      nfilt=26,nfft=512,lowfreq=0,highfreq=None,preemph=0.97)

Reference

sample english.wav obtained from:

wget http://voyager.jpl.nasa.gov/spacecraft/audio/english.au
sox english.au -e signed-integer english.wav