def _get_data_training(current_set, set_size, mixtures_list, sources_list,
window_values, fft_size, hop, seq_length,
context_length, batch_size):
"""Gets the actual input and output data for training.
:param current_set: The current set of files that we are now looking.
:type current_set: int
:param set_size: The size of the sets that we consider.
:type set_size: int
:param mixtures_list: A list with the paths of the mixtures.
:type mixtures_list: list[pathlib.Path]
:param sources_list: A list with the paths of the source.
:type sources_list: list[pathlib.Path]
:param window_values: The values of the windowing function that we will use.
:type window_values: numpy.core.multiarray.ndarray
:param fft_size: The size of the FFT in samples.
:type fft_size: int
:param hop: The hop size in samples.
:type hop: int
:param seq_length: The sequence length in frames.
:type seq_length: int
:param context_length: The context length in frames.
:type context_length: int
:param batch_size: The batch size.
:type batch_size: int
:return: The actual input and target value.
:rtype: numpy.core.multiarray.ndarray
"""
m_list = mixtures_list[(current_set - 1) * set_size:current_set * set_size]
s_list = sources_list[(current_set - 1) * set_size:current_set * set_size]
ms_train, vs_train = None, None
for index in range(len(m_list)):
mix = wav_read(m_list[index].joinpath('mixture.wav'), mono=False)[0]
vox = wav_read(s_list[index].joinpath('vocals.wav'), mono=False)[0]
ms_seg = stft(0.5 * np.sum(mix, axis=-1), window_values, fft_size,
hop)[0][3:-3, :]
vs_seg = stft(0.5 * np.sum(vox, axis=-1), window_values, fft_size,
hop)[0][3:-3, :]
if index == 0:
ms_train = ms_seg
vs_train = vs_seg
else:
ms_train = np.vstack((ms_train, ms_seg))
vs_train = np.vstack((vs_train, vs_seg))
vs_train = ideal_ratio_masking(ms_train, vs_train, ms_train) * 2.
vs_train = np.clip(vs_train, a_min=0., a_max=1.)
ms_train = np.clip(ms_train, a_min=0., a_max=1.)
ms_train, vs_train, _ = _make_overlap_sequences(ms_train, vs_train,
ms_train, seq_length,
context_length * 2,
batch_size)
return ms_train, vs_train
def _get_data_testing(sources_parent_path, window_values, fft_size, hop,
seq_length, context_length, batch_size, usage_case):
"""Gets the actual input and output data for testing.
:param sources_parent_path: The parent path of the sources
:type sources_parent_path: str
:param window_values: The values of the windowing function that we will use.
:type window_values: numpy.core.multiarray.ndarray
:param fft_size: The size of the FFT in samples.
:type fft_size: int
:param hop: The hop size in samples.
:type hop: int
:param seq_length: The sequence length in frames.
:type seq_length: int
:param context_length: The context length in frames.
:type context_length: int
:param batch_size: The batch size.
:type batch_size: int
:param usage_case: Flag to indicate that currently we are just using it.
:type usage_case: bool
:return: The actual input and target value.
:rtype: numpy.core.multiarray.ndarray
"""
if not usage_case:
bass = wav_read(os.path.join(sources_parent_path, 'bass.wav'),
mono=False)[0]
drums = wav_read(os.path.join(sources_parent_path, 'drums.wav'),
mono=False)[0]
others = wav_read(os.path.join(sources_parent_path, 'other.wav'),
mono=False)[0]
voice = wav_read(os.path.join(sources_parent_path, 'vocals.wav'),
mono=False)[0]
bg_true = np.sum(bass + drums + others, axis=-1) * 0.5
voice_true = np.sum(voice, axis=-1) * 0.5
mix = np.sum(bass + drums + others + voice, axis=-1) * 0.5
else:
mix = wav_read(sources_parent_path, mono=True)[0]
voice_true = None
bg_true = None
mix_magnitude, mix_phase = stft(mix, window_values, fft_size, hop)
# Data reshaping (magnitude and phase)
mix_magnitude, mix_phase, _ = _make_overlap_sequences(
mix_magnitude, mix_phase, mix_phase, seq_length, context_length * 2,
batch_size)
return mix, mix_magnitude, mix_phase, voice_true, bg_true