class pumpp.feature.FeatureExtractor(name, sr, hop_length, conv=None)[source]

The base feature extractor class.

name : str

The name for this feature extractor

sr : number > 0

The sampling rate of audio for analysis

hop_length : int > 0

The hop length between analysis frames

conv : {‘tf’, ‘th’, ‘channels_last’, ‘channels_first’, None}

convolution dimension ordering:

  • ‘channels_last’ for tensorflow-style 2D convolution
  • ‘tf’ equivalent to ‘channels_last’
  • ‘channels_first’ for theano-style 2D convolution
  • ‘th’ equivalent to ‘channels_first’
  • None for 1D or non-convolutional representations
__init__(name, sr, hop_length, conv=None)[source]

Initialize self. See help(type(self)) for accurate signature.


__init__(name, sr, hop_length[, conv]) Initialize self.
layers() Construct Keras input layers for the given transformer
merge(data) Merge an array of output dictionaries into a single dictionary with properly scoped names.
n_frames(duration) Get the number of frames for a given duration
phase_diff(phase) Compute the phase differential along a given axis
register(key, dimension, dtype[, channels]) Register a field as a tensor with specified shape and type.
scope(key) Apply the name scope to a key
transform(y, sr) Transform an audio signal