MFCC_windows_for_RNN_pseudocode.py

# Load wav files
fs, audio = wav.read(audio_filename)

# Get mfcc coefficients
orig_inputs = mfcc(audio, samplerate=fs, numcep=numcep)

# For each time slice of the training set, we need to copy the context this makes
train_inputs = np.array([], np.float32)
train_inputs.resize((orig_inputs.shape[0], numcep + 2 * numcep * numcontext))

for time_slice in range(train_inputs.shape[0]):
    # Pick up to numcontext time slices in the past,
    # And complete with empty mfcc features
    need_empty_past = max(0, ((time_slices[0] + numcontext) - time_slice))
    empty_source_past = list(empty_mfcc for empty_slots in range(need_empty_past))
    data_source_past = orig_inputs[max(0, time_slice - numcontext):time_slice]
    assert(len(empty_source_past) + len(data_source_past) == numcontext)
    ...