def get_waliji_feature_map(s,
log_part_blocks,
log_invpart_blocks,
abst_threshold=np.array([.025,.025,.015,.015,
.02,.02,.02,.02]),
spread_length=3,
fft_length=512,
num_window_step_samples=80,
freq_cutoff=3000,
sample_rate=16000,
num_window_samples=320,
kernel_length=7):
"""
Input is usually just the signal s as the rest of the parameters
are not going to change very often
Parameters:
===========
s: np.ndarray[ndim=1]
Raw signal data that we are extracting feature from
log_part_blocks: np.ndarray[ndim=4,dtype=np.float32]
First dimension is over the different features
log_invpart_blocks: np.ndarray[ndim=4,dtype=np.float32]
Essentially the same array as log_part_blocks. Related
by its equal to np.log(1-np.exp(log_part_blocks))
"""
S = esp.get_spectrogram_features(s,
sample_rate,
num_window_samples,
num_window_step_samples,
fft_length,
freq_cutoff,
kernel_length,
)
E, edge_feature_row_breaks,\
edge_orientations = esp._edge_map_no_threshold(S)
esp._edge_map_threshold_segments(E,
40,
1,
threshold=.7,
edge_orientations = edge_orientations,
edge_feature_row_breaks = edge_feature_row_breaks)
E = reorg_part_for_fast_filtering(E)
F = cp.code_parts_fast(E.astype(np.uint8),log_part_blocks,log_invpart_blocks,10)
F = np.argmax(F,2)
# the amount of spreading to do is governed by the size of the part features
F = swp.spread_waliji_patches(F,
log_part_blocks.shape[1],
log_part_blocks.shape[2],
log_part_blocks.shape[0])
return collapse_to_grid(F,log_part_blocks.shape[1],
log_part_blocks.shape[2])
patches_by_8 = np.array([
E[i/S.shape[1]: i/S.shape[1]+5,
i%S.shape[1]: (i%S.shape[1])+5,:]
S_patches_by_8 = np.array([
S[i/S.shape[1]: i/S.shape[1]+5,
i%S.shape[1]: i%S.shape[1]+5]
for i in patch_idx_detected_by8])
out_map = np.argmax(out_map,2)
# the amount of spreading to do is governed by the size of the part features
out_map = swp.spread_waliji_patches(out_map,
log_parts.shape[1],
log_parts.shape[2],
log_parts.shape[0])
out_map = gtrd.collapse_to_grid(out_map,log_parts.shape[1],
log_parts.shape[2])
fl_idx = 0
fl = file_indices[fl_idx]
utterance = gtrd.makeUtterance(utterances_path,fl)
S = gtrd.get_spectrogram(utterance.s,sp)
E = gtrd.get_edge_features(S.T,ep,verbose=False)
