pumpp.feature.Mel

class pumpp.feature.Mel(name, sr, hop_length, n_fft, n_mels, fmax=None, log=False, conv=None)[source]

Mel spectra feature extraction

Attributes

name (str or None) naming scope for this feature extractor
sr (number > 0) Sampling rate of the audio (in Hz)
hop_length (int > 0) Number of samples to advance between frames
n_fft ( int > 0) Number of samples per frame
n_mels (int > 0) Number of Mel frequency bins
fmax (number > 0) The maximum frequency bin. Defaults to 0.5 * sr
log (bool) If True, scale magnitude in decibels. Otherwise, use a linear amplitude scale.
__init__(name, sr, hop_length, n_fft, n_mels, fmax=None, log=False, conv=None)[source]

Methods

__init__(name, sr, hop_length, n_fft, n_mels)
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.
phase_diff(phase) Compute the phase differential along a given axis
pop(field)
register(key, dimension, dtype)
scope(key) Apply the name scope to a key
transform(y, sr) Transform an audio signal
transform_audio(y) Compute the Mel spectrogram

Attributes

idx