def get_file_indices(file_indices_path, data_path):
try:
file_indices = np.load(file_indices_path)
except:
file_indices = gtrd.get_data_files_indices(data_path)
np.save(file_indices_path, file_indices)
return file_indices
import numpy as np
root_path = '/var/tmp/stoehr/Template-Speech-Recognition/'
data_path = root_path + 'Data/'
old_exp_path = root_path + 'Notebook/1/'
old_data_path = old_exp_path + 'data/'
exp_path = root_path + 'Notebook/2/'
tmp_data_path = exp_path + 'data/'
import sys, os, cPickle
sys.path.append(root_path)
import template_speech_rec.get_train_data as gtrd
import template_speech_rec.estimate_template as et
train_data_path = root_path+'Data/Train/'
file_indices = gtrd.get_data_files_indices(train_data_path)
syllable = np.array(['aa','r'])
clipped_bgd = np.load(old_data_path+'clipped_bgd_102012.npy')
padded_examples = np.load(old_data_path+'aar_padded_examples_bgd.npy')
lengths = np.load(old_data_path+'aar_lengths.npy')
test_example_lengths = np.load(old_data_path+'test_example_lengths_102012.npy')
detection_array = np.zeros((test_example_lengths.shape[0],
test_example_lengths.max() + 2),dtype=np.float32)
sp = gtrd.SpectrogramParameters(
sample_rate=16000,
num_window_samples=320,
num_window_step_samples=80,
fft_length=512,
kernel_length=7,
freq_cutoff=3000,
use_mel=True)
ep = gtrd.EdgemapParameters(block_length=40,
spread_length=1,
threshold=.7)
utterances_path = '/home/mark/Template-Speech-Recognition/Data/Train/'
file_indices = gtrd.get_data_files_indices(utterances_path)
syllable=('aa','r')
syllable_features,avg_bgd=gtrd.get_syllable_features_directory(utterances_path,file_indices,syllable,
S_config=sp,E_config=ep,offset=0,
E_verbose=False,return_avg_bgd=True)
np.save('data/aar_bgd_mel.npy',avg_bgd.E)
example_mat = gtrd.recover_example_map(syllable_features)
lengths,waveforms = gtrd.recover_waveforms(syllable_features,example_mat)
np.savez('data/aar_waveforms_lengths.npz',waveforms,lengths,example_mat)
Slengths,Ss = gtrd.recover_specs(syllable_features,example_mat)
root_path = '/home/mark/Template-Speech-Recognition/' #root_path = '/var/tmp/stoehr/Template-Speech-Recognition/' data_path = root_path + 'Data/' old_exp_path = root_path + 'Notebook/1/' old_data_path = old_exp_path + 'data/' exp_path = root_path + 'Notebook/2/' tmp_data_path = exp_path + 'data/' import sys, os, cPickle sys.path.append(root_path) import template_speech_rec.get_train_data as gtrd import template_speech_rec.estimate_template as et file_indices = gtrd.get_data_files_indices(data_path+'Test/') num_mix = 3 i = 0 false_positive_rates =np.load(tmp_data_path+'fpr_aar_registered_new%d_%d.npy' % (num_mix,i)) true_positive_rates = np.load(tmp_data_path+'tpr_aar_registered_new%d_%d.npy' % (num_mix,i)) import matplotlib.pyplot as plt colors = ['r','b','g','y','k','m','c'] markers = ['s','o','^','>','v','<','d','p'] plt.close() plt.figure()
def get_params(
args,
sample_rate=16000,
num_window_samples=320,
num_window_step_samples=80,
fft_length=512,
kernel_length=7,
freq_cutoff=3000,
use_mel=False,
):
# we get the basic file paths right here
# TODO: make this system adaptive
root_path = "/home/mark/Template-Speech-Recognition/"
utterances_path = "/home/mark/Template-Speech-Recognition/Data/Train/"
try:
file_indices = np.load("data_parts/train_file_indices.npy")
except:
file_indices = gtrd.get_data_files_indices(utterances_path)
np.save("data_parts/train_file_indices.npy", file_indices)
num_mix_params = [1, 2, 3, 5, 7, 9]
test_path = "/home/mark/Template-Speech-Recognition/Data/Test/"
train_path = "/home/mark/Template-Speech-Recognition/Data/Train/"
try:
test_example_lengths = np.load("data_parts/test_example_lengths.npy")
test_file_indices = np.load("data_parts/test_file_indices.npy")
except:
test_file_indices = gtrd.get_data_files_indices(test_path)
test_example_lengths = gtrd.get_detect_lengths(test_file_indices, test_path)
np.save("data_parts/test_example_lengths.npy", test_example_lengths)
np.save("data_parts/test_file_indices.npy", test_file_indices)
try:
train_example_lengths = np.load("data_parts/train_example_lengths.npy")
train_file_indices = np.load("data_parts/train_file_indices.npy")
except:
train_file_indices = gtrd.get_data_files_indices(train_path)
train_example_lengths = gtrd.get_detect_lengths(train_file_indices, train_path)
np.save("data_parts/train_example_lengths.npy", train_example_lengths)
np.save("data_parts/train_file_indices.npy", train_file_indices)
return (
gtrd.SpectrogramParameters(
sample_rate=16000,
num_window_samples=320,
num_window_step_samples=80,
fft_length=512,
kernel_length=7,
freq_cutoff=3000,
use_mel=args.use_mel,
),
gtrd.makeEdgemapParameters(
block_length=args.edgeMapBlockLength,
spread_length=args.edgeMapSpreadLength,
threshold=args.edgeMapThreshold,
),
root_path,
utterances_path,
file_indices,
num_mix_params,
test_path,
train_path,
train_example_lengths,
train_file_indices,
test_example_lengths,
test_file_indices,
)
sp = gtrd.SpectrogramParameters(
sample_rate=16000,
num_window_samples=320,
num_window_step_samples=80,
fft_length=512,
kernel_length=7,
freq_cutoff=3000,
use_mel=False)
ep = gtrd.EdgemapParameters(block_length=40,
spread_length=1,
threshold=.7)
utterances_path = '/home/mark/Template-Speech-Recognition/Data/Train/'
file_indices = gtrd.get_data_files_indices(utterances_path)
syllable=('aa','r')
syllable_features,avg_bgd=gtrd.get_syllable_features_directory(utterances_path,file_indices,syllable,
S_config=sp,E_config=ep,offset=0,
E_verbose=False,return_avg_bgd=True,
waveform_offset=15)
np.save('data/aar_bgd.npy',avg_bgd.E)
example_mat = gtrd.recover_example_map(syllable_features)
lengths,waveforms = gtrd.recover_waveforms(syllable_features,example_mat)
np.savez('data/aar_waveforms_lengths.npz',waveforms,lengths,example_mat)
import scipy.io
