def experiment1_dct(num):
with open(
'select_filters/frog_data/experiment1/experiment1_train_sort_' +
str(num) + '.pkl', 'rb') as train_pkl:
train_data = pickle.load(train_pkl)
with open(
'select_filters/frog_data/experiment1/experiment1_test_' +
str(num) + '.pkl', 'rb') as test_pkl:
test_data = pickle.load(test_pkl)
_, train_data = np.hsplit(train_data, [4])
train_data, _ = np.vsplit(train_data, [20])
train_data = train_data.T
y_test, test_data = np.hsplit(test_data, [1])
train_data = dct(train_data)
train_data, _ = np.hsplit(train_data, [13])
sample = load_excel_np('audio_data/cross_validation_sample1.xlsx')
sample1 = 0
for i in range(5):
if i == num:
continue
sample1 += sample[i][0]
y_train1 = np.ones(sample1, dtype=int)
sample1 = 0
for i in range(5):
if i == num:
continue
sample1 += sample[i][1]
y_train2 = np.zeros(sample1, dtype=int)
y_train1 = np.hstack((y_train1, y_train2))
sample = load_excel_np('audio_data/cross_validation_sample2.xlsx')
sample1 = 0
for i in range(5):
if i == num:
continue
sample1 = sample1 + sample[i][0] + sample[i][1]
y_train2 = np.zeros(sample1, dtype=int)
y_train1 = np.hstack((y_train1, y_train2))
y_train = np.reshape(y_train1, (y_train1.shape[0], 1))
train_data = np.hstack((y_train, train_data))
with open(
'select_filters/frog_data/experiment1/experiment1_train_dct_' +
str(num) + '.pkl', 'wb') as training_dct_pkl:
pickle.dump(train_data, training_dct_pkl)
del train_data
test_data = dct(test_data)
test_data, _ = np.hsplit(test_data, [13])
test_data = np.hstack((y_test, test_data))
with open(
'select_filters/frog_data/experiment1/experiment1_test_dct_' +
str(num) + '.pkl', 'wb') as test_dct_pkl:
pickle.dump(test_data, test_dct_pkl)
def experiment4_set_threshold(num):
with open('select_filters/frog_data/experiment4/experiment4_train_x_'+str(num)+'.pkl', 'rb') as filters_pkl:
filters_features = pickle.load(filters_pkl)
sample2 = load_excel_np('audio_data/cross_validation_sample2.xlsx')
sample1 = load_excel_np('audio_data/cross_validation_sample1.xlsx')
sample = np.zeros(2, dtype=int)
for i in range(5):
if i == num:
continue
sample[0] += sample2[i][0]
sample[1] = sample[1] + sample2[i][1] + sample1[i][1]
threshold_data = set_threshold(filters_features, sample)
with open('select_filters/frog_data/experiment4/experiment4_train_threshold_'+str(num)+'.pkl', 'wb') as threshold_data_pkl:
pickle.dump(threshold_data , threshold_data_pkl, protocol=2)
del threshold_data
print('finished:'+str(num))
def frog1():
fs = 44100
wav_time = 120
sections = [0.1, '01']
preprocessings = ['non', 'norm1']
mfcc_dim = 12
way1 = 'pca'
way2 = 'svm'
train_sample = load_excel_np('evaluation/training_sample.xlsx')
cross_vali_sample = load_excel_np(
'evaluation/cross_validation_sample.xlsx')
for section, section_name in zip(sections[0], sections[1]):
for preprocessing in preprocessings:
out_train_path = 'mfcc/frog_data/' + section_name + '_' + preprocessing + '_train_mfcc1.pkl'
frog_training_extract_mfcc1(out_train_path, fs, mfcc_dim,
train_sample, preprocessing)
#out_test_path = 'mfcc/frog_data/'+section_name+'_'+preprocessing+'_test_mfcc.pkl'
#frog_test_extract_mfcc(out_test_path, fs, wav_time, section, mfcc_dim, preprocessing)
#ここから画像の可視化
in_train_path = 'mfcc/frog_data/' + section_name + '_' + preprocessing + '_train_mfcc1.pkl'
#in_test_path = 'mfcc/frog_data/'+section_name+'_'+preprocessing+'_test_mfcc.pkl'
out_train_path = 'mfcc/frog_data/' + section_name + '_' + preprocessing + '_train_' + way1 + '1.pkl'
#out_test_path = 'mfcc/frog_data/'+section_name+'_'+preprocessing+'_test_'+way1+'.pkl'
frog_dim_reduction(in_train_path, in_test_path, out_train_path,
out_test_path, way1, test_sample)
in_train_path = 'mfcc/frog_data/' + section_name + '_' + preprocessing + '_train_' + way1 + '1.pkl'
name = section_name + '_' + preprocessing + '_mfcc_' + way1
training_data_plot(in_train_path, test_sample[0], way1, name)
in_train_path = 'mfcc/frog_data/' + section_name + '_' + preprocessing + '_train_mfcc2.pkl'
in_test_path = 'mfcc/frog_data/' + section_name + '_' + preprocessing + '_test_mfcc.pkl'
out_predict_path = 'mfcc/frog_data/predict/' + section_name + '_' + preprocessing + '_mfcc_predict1.xlsx'
frog_classifier(in_train_path, in_test_path, out_predict_path,
way2, test_sample, wav_time, section)
predict_path = 'mfcc/frog_data/predict/' + section_name + '_' + preprocessing + '_mfcc_predict1.xlsx'
answer_path = 'evaluation/frog_sheet_' + str(section) + 's.xlsx'
result_path = 'mfcc/frog_data/predict/' + section_name + '_' + preprocessing + '_mfcc_result1.xlsx'
evaluate(predict_path, answer_path, result_path)
def frog2():
fs = 44100
wav_time = 120
sections = [[0.1, 0.5, 1.0], ['01', '05', '10']]
preprocessings = [['non', 'zscore'], ['non', 'norm1']]
nfft = 2048
hoplength = 512
filter_sample = 20
way = 'pca'
make_filters(fs, nfft)
for section, section_name in zip(sections[0], sections[1]):
test_sample = load_excel_np('evaluation/test_sample_' + str(section) +
's.xlsx')
for preprocessing1 in preprocessings[0]:
for preprocessing2 in preprocessings[1]:
out_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_filters_features2.pkl'
frog_training_stft_log_filter2(out_train_path, fs, wav_time,
section, nfft, hoplength,
preprocessing1)
in_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_filters_features2.pkl'
out_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_threshold2.pkl'
frog_set_threshold(in_train_path, out_train_path, test_sample)
in_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_threshold2.pkl'
out_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_sort2.pkl'
frog_sort(in_train_path, out_train_path)
in_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_sort2.pkl'
out_test_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_test_sort2.pkl'
frog_test_stft_log_filter(in_train_path, out_test_path, fs,
wav_time, section, nfft, hoplength,
filter_sample, preprocessing1)
in_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_sort2.pkl'
in_test_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_test_sort2.pkl'
out_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_dct2.pkl'
out_test_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_test_dct2.pkl'
frog_dct(in_train_path, in_test_path, out_train_path,
out_test_path, filter_sample, preprocessing2)
#ここから画像の可視化
in_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_dct2.pkl'
in_test_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_test_dct2.pkl'
out_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_' + way + '2.pkl'
out_test_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_test_' + way + '2.pkl'
frog_dim_reduction(in_train_path, in_test_path, out_train_path,
out_test_path, way, test_sample)
in_train_path1 = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_' + way + '2.pkl'
in_train_path2 = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_sort2.pkl'
name1 = section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_select_filters_' + way
name2 = section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_select_filter'
training_data_plot(in_train_path1, test_sample[0], way, name1)
select_filter_data_plot(in_train_path2, test_sample[0], name2)
def frog1_train_select(num):
fs = 44100
nfft = 2048
with open('haar_like/frog_data/filters.pkl', 'rb') as filters_pkl:
filters = pickle.load(filters_pkl)
filter_sample = filters.shape[0]
para_hz, filters = np.hsplit(filters, [2])
sample = load_excel_np('audio_data/cross_validation_sample1.xlsx')
filter_feature = np.empty(filter_sample)
if num != 0:
for i in range(0, sample[0][0]):
x, _ = librosa.load('audio_data/frog1/frog' + str(i) + '.wav',
sr=fs)
filter_feature1 = wav_stft_filter(x, nfft, filters)
filter_feature = np.vstack((filter_feature, filter_feature1))
if num != 1:
for i in range(sample[0][0], sample[0][0] + sample[1][0]):
x, _ = librosa.load('audio_data/frog1/frog' + str(i) + '.wav',
sr=fs)
filter_feature1 = wav_stft_filter(x, nfft, filters)
filter_feature = np.vstack((filter_feature, filter_feature1))
if num != 2:
for i in range(sample[0][0] + sample[1][0],
sample[0][0] + sample[1][0] + sample[2][0]):
x, _ = librosa.load('audio_data/frog1/frog' + str(i) + '.wav',
sr=fs)
filter_feature1 = wav_stft_filter(x, nfft, filters)
filter_feature = np.vstack((filter_feature, filter_feature1))
if num != 3:
for i in range(
sample[0][0] + sample[1][0] + sample[2][0],
sample[0][0] + sample[1][0] + sample[2][0] + sample[3][0]):
x, _ = librosa.load('audio_data/frog1/frog' + str(i) + '.wav',
sr=fs)
filter_feature1 = wav_stft_filter(x, nfft, filters)
filter_feature = np.vstack((filter_feature, filter_feature1))
if num != 4:
for i in range(
sample[0][0] + sample[1][0] + sample[2][0] + sample[3][0],
sample[0][0] + sample[1][0] + sample[2][0] + sample[3][0] +
sample[4][0]):
x, _ = librosa.load('audio_data/frog1/frog' + str(i) + '.wav',
sr=fs)
filter_feature1 = wav_stft_filter(x, nfft, filters)
filter_feature = np.vstack((filter_feature, filter_feature1))
filter_feature = np.delete(filter_feature, obj=0, axis=0)
filter_feature = np.hstack((para_hz, filter_feature.T))
with open('haar_like/frog_data/frog1/frog1_train_' + str(num) + '.pkl',
'wb') as train_mfcc_pkl:
pickle.dump(filter_feature, train_mfcc_pkl, protocol=2)
del filter_feature
print('finished:' + str(num))
def frog1():
fs = 44100
wav_time = 120
sections = [[0.1, 0.5, 1.0], ['01', '05', '10']]
preprocessings = [['non', 'zscore'], ['non', 'norm1']]
nfft = 2048
hoplength = 512
filter_sample = 20
way = 'pca'
train_sample = load_excel_np('evaluation/training_sample.xlsx')
cross_vali_sample = load_excel_np(
'evaluation/cross_validation_sample.xlsx')
for section, section_name in zip(sections[0], sections[1]):
test_sample = load_excel_np('evaluation/test_sample_' + str(section) +
's.xlsx')
for preprocessing1 in preprocessings[0]:
for preprocessing2 in preprocessings[1]:
out_train_path = 'select_filters/frog_data/' + section_name + '_' + preprocessing1 + '_' + preprocessing2 + '_train_filters_features2.pkl'
frog_training_stft_log_filter2(out_train_path, fs, wav_time,
section, nfft, hoplength,
preprocessing1)
def frog_training_stft_filter(fs, nfft, wav_time, section):
cross_validation = 5
with open('haar_like/frog_data/filters_' + str(nfft) + '.pkl',
'rb') as filters_pkl:
filters_x = pickle.load(filters_pkl)
filter_sample = filters_x.shape[0]
para_hz, filters = np.hsplit(filters_x, [2])
split_sample = int(wav_time / section)
split_interval = int(fs * section)
evaluation = load_excel_np('evaluation/frog_sheet_' + str(section) +
's.xlsx')
filters_features = []
for i in range(cross_validation):
filters_features1 = np.empty(filter_sample)
training_evaluation = np.empty(1, int)
for j in range(cross_validation):
if i == j:
continue
x, f = librosa.load('test_data/frog' + str(j + 1) + '.wav',
sr=fs)
for k in range(split_sample):
x_split = x[k * split_interval:(k + 1) * split_interval]
filters_features2 = wav_stft_filter(x_split, nfft, filters)
filters_features1 = np.vstack(
(filters_features1, filters_features2
)) # features[split_sample][filter_sample]
training_evaluation = np.hstack(
(training_evaluation, evaluation[j]))
filters_features1 = np.delete(filters_features1, 0,
0) # delite [0][]
training_evaluation = training_evaluation[1:]
training_evaluation = training_evaluation.reshape(
(split_sample * 4, 1))
filters_features1 = np.hstack(
(training_evaluation, filters_features1))
filters_features1 = filters_features1[np.argsort(
filters_features1[:, 0])[::-1]]
filters_features1 = np.delete(filters_features1, obj=0, axis=1)
filters_features1 = np.hstack((para_hz, filters_features1.T))
filters_features.append(filters_features1)
print('finished:frog_training_stft_filter')
return filters_features
def VAD_MFCC():
fs = 44100
wav_time = 120
nfft = 2048
sections = [[0.1, 0.5, 1.0], ['01', '05', '10']]
for section, section_name in zip(sections[0], sections[1]):
test_sample = load_excel_np('evaluation/test_sample_' + str(section) +
's.xlsx')
#MFCCを抽出
train_mfcc = frog_training_extract_mfcc(fs, nfft, wav_time, section)
test_mfcc = frog_test_extract_mfcc(fs, nfft, wav_time, section)
#図を作成
train_pca, test_pca = frog_dim_reduction(train_mfcc, test_mfcc, 'pca',
test_sample)
name = section_name + '_mfcc'
training_data_plot('mfcc', train_pca[0], test_sample[0], 'pca', name)
#識別器で分類
#SVM
out_predict_path = 'mfcc/predict/predict_' + section_name + '_mfcc_svm.xlsx'
frog_classifier(train_mfcc, test_mfcc, out_predict_path, 'svm',
test_sample, wav_time, section)
predict_path = 'mfcc/predict/predict_' + section_name + '_mfcc_svm.xlsx'
answer_path = 'evaluation/frog_sheet_' + str(section) + 's.xlsx'
result_path = 'mfcc/predict/result_' + section_name + '_mfcc_svm.xlsx'
evaluate(predict_path, answer_path, result_path)
#lda->normal distribution
train_lda, test_lda = frog_dim_reduction(train_mfcc, test_mfcc, 'lda',
test_sample)
out_predict_path = 'mfcc/predict/predict_' + section_name + '_mfcc_lda.xlsx'
frog_classifier(train_lda, test_lda, out_predict_path, 'lda',
test_sample, wav_time, section)
predict_path = 'mfcc/predict/predict_' + section_name + '_mfcc_lda.xlsx'
answer_path = 'evaluation/frog_sheet_' + str(section) + 's.xlsx'
result_path = 'mfcc/predict/result_' + section_name + '_mfcc_lda.xlsx'
evaluate(predict_path, answer_path, result_path)
plt.scatter(x=training_sort[i, 4:4 + sample[0]],
y=y_train,
color="blue",
marker="o",
label="fg") # fg...o,blue,0
y_train = np.ones(sample[1])
plt.scatter(x=training_sort[i, 4 + sample[0]:],
y=y_train,
color="red",
marker="x",
label="no") # no...x,red,1
plt.axvline(training_sort[i][1],
color="green") # threshold...green
plt.legend() # 凡例を表示
plt.savefig('select_filters/pictures/' + name + '_' + str(i + 1))
plt.clf()
plt.close()
if __name__ == '__main__':
in_train_path1 = 'select_filters/frog_data/training_pca2.pkl'
in_train_path2 = 'select_filters/frog_data/training_sort2.pkl'
section = 0.5
test_sample = load_excel_np('evaluation/test_sample_' + str(section) +
's.xlsx')
way = 'pca'
name1 = 'select_filters_05_pca'
name2 = 'select_filter_05'
filter_sample = 6
training_data_plot(in_train_path1, test_sample[0], way, name1)
select_filter_data_plot(in_train_path2, test_sample[0], name2)
return predict
def frog_classifier(train_data_x, test_data_x, out_predict_path, way, sample, wav_time, section):
cross_validation = 5
split_sample = int(wav_time / section)
predict = np.empty(split_sample, dtype=int)
if way == 'svm':
for i in range(cross_validation):
predict1 = linear_svm(train_data_x[i], test_data_x[i], sample[i])
predict = np.vstack((predict, predict1))
predict = np.delete(predict, obj=0, axis=0)
np_excel(predict, out_predict_path)
print('finished:predict_'+way)
elif way == 'pca' or way =='lda':
for i in range(cross_validation):
predict1 = normal_distribution_predict(train_data_x[i], test_data_x[i], way, sample[i])
predict = np.vstack((predict, predict1))
predict = np.delete(predict, obj=0, axis=0)
np_excel(predict, out_predict_path)
print('finished:predict_'+way)
if __name__ == '__main__':
in_train_path = 'mfcc/frog_data/05_non_non_train_mfcc2.pkl'
in_test_path = 'mfcc/frog_data/05_non_non_test_mfcc.pkl'
out_predict_path = 'mfcc/predict.xlsx'
way = 'svm'
test_sample = load_excel_np('evaluation/test_sample_0.5s.xlsx')
wav_time = 120
section = 0.5
frog_classifier(in_train_path, in_test_path, out_predict_path, way, test_sample, wav_time, section)
def frog2_test_mfcc(num):
fs = 192000
nfft = 8192
with open('mfcc/frog_data/experiment2/melfilterbank2.pkl', 'rb') as filterbank_pkl:
melfilterbank = pickle.load(filterbank_pkl)
del filterbank_pkl
sample = load_excel_np('audio_data/cross_validation_sample2.xlsx')
mfcc = np.empty((np.sum(sample[num]), 13))
mfcc_count = 0
if num == 0:
for i in range(0, sample[0][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 1
mfcc_count += 1
for i in range(0, sample[0][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
for i in range(0, sample[0][2]):
x, _ = librosa.load('audio_data/frog3/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
if num == 1:
for i in range(sample[0][0], sample[0][0]+sample[1][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 1
mfcc_count += 1
for i in range(sample[0][1], sample[0][1]+sample[1][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
for i in range(sample[0][2], sample[0][2]+sample[1][2]):
x, _ = librosa.load('audio_data/frog3/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
if num == 2:
for i in range(sample[0][0]+sample[1][0], sample[0][0]+sample[1][0]+sample[2][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 1
mfcc_count += 1
for i in range(sample[0][1]+sample[1][1], sample[0][1]+sample[1][1]+sample[2][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
for i in range(sample[0][2]+sample[1][2], sample[0][2]+sample[1][2]+sample[2][2]):
x, _ = librosa.load('audio_data/frog3/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
if num == 3:
for i in range(sample[0][0]+sample[1][0]+sample[2][0], sample[0][0]+sample[1][0]+sample[2][0]+sample[3][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 1
mfcc_count += 1
for i in range(sample[0][1]+sample[1][1]+sample[2][1], sample[0][1]+sample[1][1]+sample[2][1]+sample[3][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
for i in range(sample[0][2]+sample[1][2]+sample[2][2], sample[0][2]+sample[1][2]+sample[2][2]+sample[3][2]):
x, _ = librosa.load('audio_data/frog3/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
if num == 4:
for i in range(sample[0][0]+sample[1][0]+sample[2][0]+sample[3][0], sample[0][0]+sample[1][0]+sample[2][0]+sample[3][0]+sample[4][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 1
mfcc_count += 1
for i in range(sample[0][1]+sample[1][1]+sample[2][1]+sample[3][1], sample[0][1]+sample[1][1]+sample[2][1]+sample[3][1]+sample[4][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
for i in range(sample[0][2]+sample[1][2]+sample[2][2]+sample[3][2], sample[0][2]+sample[1][2]+sample[2][2]+sample[3][2]+sample[4][2]):
x, _ = librosa.load('audio_data/frog3/back'+str(i)+'.wav', sr=fs)
mfcc[mfcc_count][1:13] = wav_mfcc(x, nfft, melfilterbank)
mfcc[mfcc_count][0] = 0
mfcc_count += 1
with open('mfcc/frog_data/experiment2/test_mfcc'+str(num)+'.pkl', 'wb') as test_mfcc_pkl:
pickle.dump(mfcc, test_mfcc_pkl, protocol=2)
del mfcc
del test_mfcc_pkl
print('finished:test_mfcc'+str(num))
def experiment4_train_mfcc(num):
fs = 44100
nfft = 2048
sample1 = load_excel_np('audio_data/cross_validation_sample2.xlsx')
sample2 = load_excel_np('audio_data/cross_validation_sample1.xlsx')
mfcc = np.empty(13)
if num != 0:
for i in range(0, sample1[0][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(0, sample1[0][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(0, sample2[0][1]):
x, _ = librosa.load('audio_data/frog1/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
if num != 1:
for i in range(sample1[0][0], sample1[0][0]+sample1[1][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(sample1[0][1], sample1[0][1]+sample1[1][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(sample2[0][1], sample2[0][1]+sample2[1][1]):
x, _ = librosa.load('audio_data/frog1/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
if num != 2:
for i in range(sample1[0][0]+sample1[1][0], sample1[0][0]+sample1[1][0]+sample1[2][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(sample1[0][1]+sample1[1][1], sample1[0][1]+sample1[1][1]+sample1[2][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(sample2[0][1]+sample2[1][1], sample2[0][1]+sample2[1][1]+sample2[2][1]):
x, _ = librosa.load('audio_data/frog1/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
if num != 3:
for i in range(sample1[0][0]+sample1[1][0]+sample1[2][0], sample1[0][0]+sample1[1][0]+sample1[2][0]+sample1[3][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(sample1[0][1]+sample1[1][1]+sample1[2][1], sample1[0][1]+sample1[1][1]+sample1[2][1]+sample1[3][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(sample2[0][1]+sample2[1][1]+sample2[2][1], sample2[0][1]+sample2[1][1]+sample2[2][1]+sample2[3][1]):
x, _ = librosa.load('audio_data/frog1/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
if num != 4:
for i in range(sample1[0][0]+sample1[1][0]+sample1[2][0]+sample1[3][0], sample1[0][0]+sample1[1][0]+sample1[2][0]+sample1[3][0]+sample1[4][0]):
x, _ = librosa.load('audio_data/frog2/frog'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(sample1[0][1]+sample1[1][1]+sample1[2][1]+sample1[3][1], sample1[0][1]+sample1[1][1]+sample1[2][1]+sample1[3][1]+sample1[4][1]):
x, _ = librosa.load('audio_data/frog2/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
for i in range(sample2[0][1]+sample2[1][1]+sample2[2][1]+sample2[3][1], sample2[0][1]+sample2[1][1]+sample2[2][1]+sample2[3][1]+sample2[4][1]):
x, _ = librosa.load('audio_data/frog1/back'+str(i)+'.wav', sr=fs)
mfcc1 = wav_mfcc(x, nfft)
mfcc = np.vstack((mfcc, mfcc1))
mfcc = np.delete(mfcc, obj=0, axis=0)
y_test1 = np.empty(1, dtype=int)
for i in range(5):
if i == num:
continue
y_test2 = np.ones(sample1[i][0], dtype=int)
y_test1 = np.hstack((y_test1, y_test2))
y_test2 = np.zeros(sample1[i][1]+sample2[i][1], dtype=int)
y_test1 = np.hstack((y_test1, y_test2))
y_test1 = y_test1[1:]
y_test = np.reshape(y_test1, (y_test1.shape[0], 1))
mfcc = np.hstack((y_test, mfcc))
with open('mfcc/frog_data/experiment4/experiment4_train_mfcc_'+str(num)+'.pkl', 'wb') as train_mfcc_pkl:
pickle.dump(mfcc, train_mfcc_pkl, protocol=2)
del mfcc
del train_mfcc_pkl
print('finished:4_train_mfcc'+str(num))
