BEAT - elie_khoury/cepstral/2

This algorithm is a legacy one. The API has changed since its implementation. New versions and forks will need to be updated.

Endpoint Groups 1

Algorithms have at least one input and one output. All algorithm endpoints are organized in groups. Groups are used by the platform to indicate which inputs and outputs are synchronized together. The first group is automatically synchronized with the channel defined by the block in which the algorithm is deployed.

Unnamed group

Endpoint Name	Data Format	Nature
speech	system/array_1d_floats/1	Input
vad	system/array_1d_integers/1	Input
features	system/array_2d_floats/1	Output

Parameters 1

Parameters allow users to change the configuration of an algorithm when scheduling an experiment

Name	Description	Type	Default	Range/Choices
rate		float64	16000.0

import bob
import numpy

def normalize_std_array(vector):
  """Applies a unit mean and variance normalization to an arrayset"""

# Initializes variables
  length = 1
  n_samples = len(vector)
  mean = numpy.ndarray((length,), 'float64')
  std = numpy.ndarray((length,), 'float64')

mean.fill(0)
  std.fill(0)

# Computes mean and variance
  for array in vector:
    x = array.astype('float64')
    mean += x
    std += (x ** 2)

mean /= n_samples
  std /= n_samples
  std -= (mean ** 2)
  std = std ** 0.5 
  arrayset = numpy.ndarray(shape=(n_samples,mean.shape[0]), dtype=numpy.float64)
  
  for i in range (0, n_samples):
    arrayset[i,:] = (vector[i]-mean) / std 
  return arrayset

class Algorithm:

def __init__(self):
    self.win_length_ms = 20
    self.win_shift_ms = 10
    self.n_filters = 24
    self.n_ceps = 19
    self.f_min = 0 
    self.f_max = 4000
    self.delta_win = 2
    self.pre_emphasis_coef = 0.95
    self.dct_norm = False
    self.mel_scale = True
    self.withEnergy = True
    self.withDelta = True
    self.withDeltaDelta = True
    #TODO: find a way to compute this automatically
    self.rate = 16000
    self.features_mask = numpy.arange(0,60)
    self.normalizeFeatures = True

def setup(self, parameters):
    self.rate = parameters.get('rate', self.rate)
    wl = self.win_length_ms
    ws = self.win_shift_ms
    nf = self.n_filters
    nc = self.n_ceps
    f_min = self.f_min
    f_max = self.f_max
    dw = self.delta_win
    pre = self.pre_emphasis_coef
    rate = self.rate
    normalizeFeatures = self.normalizeFeatures
    self.extractor = bob.ap.Ceps(rate, wl, ws, nf, nc, f_min, f_max, dw, pre)
    self.extractor.dct_norm = self.dct_norm
    self.extractor.mel_scale = self.mel_scale
    self.extractor.with_energy = self.withEnergy
    self.extractor.with_delta = self.withDelta
    self.extractor.with_delta_delta = self.withDeltaDelta

return True

def normalize_features(self, params):
  #########################
  ## Initialisation part ##
  #########################
    normalized_vector = [ [ 0 for i in range(params.shape[1]) ] for j in range(params.shape[0]) ] 
    for index in range(params.shape[1]):
      vector = numpy.array([row[index] for row in params])
      n_samples = len(vector)
      norm_vector = normalize_std_array(vector)
    
      for i in range(n_samples):
        normalized_vector[i][index]=numpy.asscalar(norm_vector[i])  
    data = numpy.array(normalized_vector)
    return data
  
  
  def process(self, inputs, outputs):
    
    float_wav = inputs["speech"].data.value
    labels = inputs["vad"].data.value
    
    cepstral_features = self.extractor(float_wav)
    features_mask = self.features_mask
    filtered_features = numpy.ndarray(shape=((labels == 1).sum(),len(features_mask)), dtype=numpy.float64)
    i=0
    cur_i=0

for row in cepstral_features:
      if i < len(labels):
        if labels[i]==1:
          for k in range(len(features_mask)):
            filtered_features[cur_i,k] = row[features_mask[k]]
          cur_i = cur_i + 1
        i = i+1
      else:
        if labels[-1]==1:
          if cur_i == cepstral_features.shape[0]:
            for k in range(len(features_mask)):
              filtered_features[cur_i,k] = row[features_mask[k]]
            cur_i = cur_i + 1
        i = i+1
    if self.normalizeFeatures:
      normalized_features = self.normalize_features(filtered_features)
    else:
      normalized_features = filtered_features
    if normalized_features.shape[0] == 0:
      print("Warning: no speech found in: %s" % input_file)
      # But do not keep it empty!!! This avoids errors in next steps
      normalized_features=numpy.array([numpy.zeros(len(features_mask))])

outputs["features"].write({
      'value': numpy.vstack(normalized_features)
    })

return True

The code for this algorithm in Python
The ruler at 80 columns indicate suggested POSIX line breaks (for readability).
The editor will automatically enlarge to accomodate the entirety of your input
Use keyboard shortcuts for search/replace and faster editing. For example, use Ctrl-F (PC) or Cmd-F (Mac) to search through this box

This algorithm implements the MFCC and LFCC feature extraction. It relies on the Bob library.

The following parameters are set inside the algorithm and can be modified by the user:

'win_length_ms': length of the processing window
'win_shift_ms': length of the shift
'n_filters': number of filters
'n_ceps': number of cepstal coefficients
'f_min': minimum frequency
'f_max': maximum frequency
'delta_win': window on which first and second derivatives are computed
'pre_emphasis_coeff': pre-emphasis coefficient
'mel_scale': flag for Mel scale
'dct_norm': DCT normalization
'with_delta': flag for computing the first derivatives
'with_delta_delta': flag for computing the second derivatives
'with_energy': flag for computing the energy
'features_mask': mask to use only a sub-set of features
'normalizeFeatures': flag to do zero-mean and variance normalization

No experiments are using this algorithm.

This algorithm was never executed.

algorithms elie_khoury cepstral 2

Endpoint Groups 1

Unnamed group

Parameters 1

algorithms

elie_khoury

cepstral

2