astorfi/speechpy

def mfcc(signal, sampling_frequency, frame_length=0.020, frame_stride=0.01,num_cepstral =13,
       num_filters=40, fft_length=512, low_frequency=0, high_frequency=None, dc_elimination=True):
      """Compute MFCC features from an audio signal.
      :param signal: the audio signal from which to compute features. Should be an N x 1 array
      :param sampling_frequency: the sampling frequency of the signal we are working with.
      :param frame_length: the length of each frame in seconds. Default is 0.020s
      :param frame_stride: the step between successive frames in seconds. Default is 0.02s (means no overlap)
      :param num_filters: the number of filters in the filterbank, default 40.
      :param fft_length: number of FFT points. Default is 512.
      :param low_frequency: lowest band edge of mel filters. In Hz, default is 0.
      :param high_frequency: highest band edge of mel filters. In Hz, default is samplerate/2
      :param num_cepstral: Number of cepstral coefficients.
      :param dc_elimination: hIf the first dc component should be eliminated or not.
      :returns: A numpy array of size (num_frames x num_cepstral) containing mfcc features.
      """

def mfe(signal, sampling_frequency, frame_length=0.020, frame_stride=0.01,
          num_filters=40, fft_length=512, low_frequency=0, high_frequency=None):
    """Compute Mel-filterbank energy features from an audio signal.
    :param signal: the audio signal from which to compute features. Should be an N x 1 array
    :param sampling_frequency: the sampling frequency of the signal we are working with.
    :param frame_length: the length of each frame in seconds. Default is 0.020s
    :param frame_stride: the step between successive frames in seconds. Default is 0.02s (means no overlap)
    :param num_filters: the number of filters in the filterbank, default 40.
    :param fft_length: number of FFT points. Default is 512.
    :param low_frequency: lowest band edge of mel filters. In Hz, default is 0.
    :param high_frequency: highest band edge of mel filters. In Hz, default is samplerate/2
    :returns:
              features: the energy of fiterbank: num_frames x num_filters
              frame_energies: the energy of each frame: num_frames x 1
    """

def lmfe(signal, sampling_frequency, frame_length=0.020, frame_stride=0.01,
     num_filters=40, fft_length=512, low_frequency=0, high_frequency=None):
    """Compute log Mel-filterbank energy features from an audio signal.
    :param signal: the audio signal from which to compute features. Should be an N x 1 array
    :param sampling_frequency: the sampling frequency of the signal we are working with.
    :param frame_length: the length of each frame in seconds. Default is 0.020s
    :param frame_stride: the step between successive frames in seconds. Default is 0.02s (means no overlap)
    :param num_filters: the number of filters in the filterbank, default 40.
    :param fft_length: number of FFT points. Default is 512.
    :param low_frequency: lowest band edge of mel filters. In Hz, default is 0.
    :param high_frequency: highest band edge of mel filters. In Hz, default is samplerate/2
    :returns:
              features: the energy of fiterbank: num_frames x num_filters
              frame_log_energies: the log energy of each frame: num_frames x 1
    """

def stack_frames(sig, sampling_frequency, frame_length=0.020, frame_stride=0.020, Filter=lambda x: numpy.ones((x,)),
         zero_padding=True):
    """Frame a signal into overlapping frames.
    :param sig: The audio signal to frame of size (N,).
    :param sampling_frequency: The sampling frequency of the signal.
    :param frame_length: The length of the frame in second.
    :param frame_stride: The stride between frames.
    :param Filter: The time-domain filter for applying to each frame. By default it is one so nothing will be changed.
    :param zero_padding: If the samples is not a multiple of frame_length(number of frames sample), zero padding will
                         be done for generating last frame.
    :returns: Array of frames. size: number_of_frames x frame_len.
    """

def cmvn(vec, variance_normalization=False):
    """
    This function is aimed to perform global ``cepstral mean and variance normalization``
    (CMVN) on input feature vector "vec". The code assumes that there is one observation per row.

    :param:
          vec: input feature matrix (size:(num_observation,num_features))
          variance_normalization: If the variance normilization should be performed or not.
    :return:
          The mean(or mean+variance) normalized feature vector.
    """

def cmvnw(vec, win_size=301, variance_normalization=False):
    """
    This function is aimed to perform local cepstral mean and variance normalization on a sliding window.
    (CMVN) on input feature vector "vec". The code assumes that there is one observation per row.
    :param
          vec: input feature matrix (size:(num_observation,num_features))
          win_size: The size of sliding window for local normalization and should be odd.
                    default=301 which is around 3s if 100 Hz rate is considered(== 10ms frame stide)
          variance_normalization: If the variance normilization should be performed or not.

    :return: The mean(or mean+variance) normalized feature vector.
    """

import scipy.io.wavfile as wav
import numpy as np
import speechpy
import os

file_name = os.path.join(os.path.dirname(os.path.abspath(__file__)),'Alesis-Sanctuary-QCard-AcoustcBas-C2.wav')
fs, signal = wav.read(file_name)
signal = signal[:,0]

# Example of pre-emphasizing.
signal_preemphasized = speechpy.processing.preemphasis(signal, cof=0.98)

# Example of staching frames
frames = speechpy.processing.stack_frames(signal, sampling_frequency=fs, frame_length=0.020, frame_stride=0.01, filter=lambda x: np.ones((x,)),
         zero_padding=True)

# Example of extracting power spectrum
power_spectrum = speechpy.processing.power_spectrum(frames, fft_points=512)
print('power spectrum shape=', power_spectrum.shape)

############# Extract MFCC features #############
mfcc = speechpy.feature.mfcc(signal, sampling_frequency=fs, frame_length=0.020, frame_stride=0.01,
             num_filters=40, fft_length=512, low_frequency=0, high_frequency=None)
mfcc_cmvn = speechpy.processing.cmvnw(mfcc,win_size=301,variance_normalization=True)
print('mfcc(mean + variance normalized) feature shape=', mfcc_cmvn.shape)

mfcc_feature_cube = speechpy.feature.extract_derivative_feature(mfcc)
print('mfcc feature cube shape=', mfcc_feature_cube.shape)

############# Extract logenergy features #############
logenergy = speechpy.feature.lmfe(signal, sampling_frequency=fs, frame_length=0.020, frame_stride=0.01,
             num_filters=40, fft_length=512, low_frequency=0, high_frequency=None)
logenergy_feature_cube = speechpy.feature.extract_derivative_feature(logenergy)
print('logenergy features=', logenergy.shape)