def train():
warnings.filterwarnings("ignore")
# path to training data
source = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\Training\\"
modelpath = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\TestSource\\"
dest_dir = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\Tilak\\wav\\"
test_file = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\test.txt"
prefix = "Tilak\\wav\\"
file_paths = open(test_file, 'r')
record_audio("testVoice", dest_dir)
enroll_edit("testVoice", test_file, prefix)
gmm_files = [
os.path.join(source, fname) for fname in os.listdir(source)
if fname.endswith('.gmm')
]
# load model
models = [cpk.load(open(fname, 'rb')) for fname in gmm_files]
speakers = [fname.split("\\")[-1].split(".gmm")[0] for fname in gmm_files]
sr, audio = read(dest_dir + "testVoice.wav")
vector = extract_features(audio, sr)
def validate(user_name):
source = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Test\\"
os.makedirs(
"C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Test\\" +
user_name + "\\wav\\")
f = open(
"C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Test\\" +
user_name + "\\test.txt", 'w')
test_file = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Test\\" + user_name + "\\test.txt"
dir_test = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Test\\" + user_name + "\\wav\\"
gmm_dir = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Enroll\\" + user_name + "\\"
prefix_test = user_name + "\\wav\\"
f_name1 = user_name + "test"
record_audio(f_name1, dir_test)
edit_txt(f_name1, test_file, prefix_test)
file_paths1 = open(test_file, 'r')
gmm_files = gmm_dir + user_name + ".gmm"
# Load the Gaussian gender Models
models = cpk.load(open(gmm_files, 'rb'))
# Read the test directory and get the list of test audio files
for path1 in file_paths1:
print(path1[:-1])
path1 = path1[:-1]
(sr, audio) = read(source + path1)
vector = extract_features(audio, sr)
log_likelihood = np.zeros(1)
gmm = models # checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[0] = scores.sum()
print(log_likelihood[0])
if ((logavg / log_likelihood[0]) * 100) > 50:
print("legit user")
else:
print("Invalid user")
prefix_train = user_name + "\\Train\\wav\\"
os.makedirs("C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\" +
user_name + "\\Test\\wav\\")
test_file = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\test.txt"
dest_dir_test = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\" + user_name + "\\Test\\wav\\"
gmm_dir_test = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\" + user_name + "\\Test\\"
prefix_test = user_name + "\\Test\\wav\\"
print("Welcome " + user_name)
for i in range(3):
trial = "trial" + str(i + 1)
print(trial)
f_name = user_name + str(i + 1)
record_audio(f_name, dest_dir_train)
edit_txt(f_name, train_file, prefix_train)
file_paths = open(train_file, 'r')
count = 1
features = np.asarray(())
for path in file_paths:
path = path.strip()
print(path)
def enroll(user_name):
source = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Enroll\\"
os.makedirs(
"C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Enroll\\" +
user_name + "\\wav\\")
train_dir = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Enroll\\" + user_name + "\\wav\\"
gmm_dir = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Enroll\\" + user_name + "\\"
prefix_train = user_name + "\\wav\\"
f = open(
"C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Enroll\\" +
user_name + "\\enroll.txt", 'w')
enroll_file = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\22apr2018\\Enroll\\" + user_name + "\\enroll.txt"
global logavg
print("Welcome" + user_name)
for i in range(3):
trial = "trial" + str(i + 1)
print(trial)
key_phrase = rand_phrase()
print("Please say '" + key_phrase +
"' once the system starts listening")
time.sleep(2)
f_name = user_name + str(i + 1)
record_audio(f_name, train_dir)
edit_txt(f_name, enroll_file, prefix_train)
file_paths = open(enroll_file, 'r')
file_paths1 = open(enroll_file, 'r')
count = 1
features = np.asarray(())
for path in file_paths:
path = path.strip()
print(path)
# read the audio
sr, audio = read(source + path)
# extract 40 dimensional MFCC & delta MFCC features
vector = extract_features(audio, sr)
if features.size == 0:
features = vector
else:
features = np.vstack((features, vector))
# when features of 3 files of speaker are concatenated, then do model training
if count == 3:
gmm = GMM(n_components=16,
n_iter=200,
covariance_type='diag',
n_init=3)
gmm.fit(features)
# dumping the trained gaussian model
picklefile = user_name + ".gmm"
cpk.dump(gmm, open(gmm_dir + picklefile, 'wb'))
print('+ modeling completed for speaker:', picklefile,
" with data point = ", features.shape)
features = np.asarray(())
count = 0
count = count + 1
gmm_files = gmm_dir + user_name + ".gmm"
models = cpk.load(open(gmm_files, 'rb'))
logsum = 0
for path1 in file_paths1:
path1 = path1.strip()
print(path1)
(sro, audioo) = read(source + path1)
vector_o = extract_features(audioo, sro)
log_likelihood_orig = np.zeros(1)
gmm = models # checking with each model one by one
scores = np.array(gmm.score(vector_o))
log_likelihood_orig[0] = scores.sum()
print(log_likelihood_orig[0])
logsum = logsum + log_likelihood_orig[0]
logavg = logsum / 3
print(logavg)
del_txt(enroll_file)
return logavg
dest_dir = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\Tilak\\wav\\"
train_file = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\enroll.txt"
prefix = "Tilak\\wav\\"
features = np.asarray(())
user_name = input("Enter username")
print("Welcome " + user_name)
for i in range(3):
trial = "trial" + str(i + 1)
print(trial)
f_name = user_name + str(i + 1)
record_audio(f_name, dest_dir)
enroll_edit(f_name, train_file, prefix)
file_paths = open(train_file, 'r')
count = 1
for path in file_paths:
path = path.strip()
print(path)
# read the audio
sr, audio = read(source + path)
# extract 40 dimensional MFCC & delta MFCC features
vector = extract_features(audio, sr)
os.makedirs("C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\" + user_name + "\\Test\\wav\\")
test_file = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\test.txt"
dest_dir_test = "C:\\Users\\Tilak1114\\Desktop\\DEVHACK2018\\18apr2018\\" + user_name + "\\Test\\wav\\"
prefix_test = user_name + "\\Test\\wav\\"
print("Welcome "+user_name)
for i in range(3): # 3 inputs
trial = "trial"+str(i+1)
print(trial)
f_name = user_name+str(i+1)
record_audio(f_name, dest_dir_train) # record audio
edit_txt(f_name, train_file, prefix_train) # write to train/enroll.txt
file_paths = open(train_file, 'r') # read enroll.txt
count = 1
features = np.asarray(())
for path in file_paths: # iterate 3 times cuz 3 audio files
path = path.strip()
print(path)
# read the audio
sr, audio = read(source + path)
# extract 40 dimensional MFCC & delta MFCC features
def enroll(user_name):
source_enroll = "..\\Enroll\\"
os.makedirs("..\\Enroll\\" + user_name + "\\wav\\")
train_dir = "..\\Enroll\\" + user_name + "\\wav\\"
gmm_dir = "..\\Enroll\\" + user_name + "\\"
prefix_train = user_name + "\\wav\\"
f = open("..\\Enroll\\" + user_name + "\\enroll.txt", 'w')
enroll_file = "..\\Enroll\\" + user_name + "\\enroll.txt"
print("Welcome" + user_name)
for i in range(5):
trial = "trial" + str(i + 1)
print(trial)
key_phrase = rand_phrase_train()
print("Please say '" + key_phrase +
"' once the system starts listening")
time.sleep(2)
f_name = user_name + str(i + 1)
record_audio(f_name, train_dir)
edit_txt(f_name, enroll_file, prefix_train)
file_paths = open(enroll_file, 'r')
count = 1
features = np.asarray(())
for path in file_paths:
path = path.strip()
print(path)
# read the audio
sr, audio = read(source_enroll + path)
# extract 40 dimensional MFCC & delta MFCC features
vector = extract_features(audio, sr)
if features.size == 0:
features = vector
else:
features = np.vstack((features, vector))
# when features of 5 files of speaker are concatenated, then do model training
if count == 5:
gmm = GMM(n_components=8,
n_iter=200,
covariance_type='diag',
n_init=3)
gmm.fit(features)
# dumping the trained gaussian model
picklefile = user_name + ".gmm"
cpk.dump(gmm, open(gmm_dir + picklefile, 'wb'))
print('+ modeling completed for speaker:', picklefile,
" with data point = ", features.shape)
features = np.asarray(())
count = 0
count = count + 1
def validate(user_name):
global log_likelihood
log_likelihood = np.zeros(1)
source_enroll = "..\\Enroll\\"
source_test = "..\\Test\\"
os.makedirs("..\\Test\\" + user_name + "\\wav\\")
f = open("..\\Test\\" + user_name + "\\test.txt", 'w')
test_file = "..\\Test\\" + user_name + "\\test.txt"
dir_test = "..\\Test\\" + user_name + "\\wav\\"
gmm_dir = "..\\Enroll\\" + user_name + "\\"
enroll_file = "..\\Enroll\\" + user_name + "\\enroll.txt"
prefix_test = user_name + "\\wav\\"
# ead = input("Enter email address so that an otp can be sent:")
# pwd = input("enter your mails password")
messg = rand_phrase_test()
# sendotph(ead, pwd, messg)
rt = input(
"Are you ready to validate? hit 'y' if you have the key-phrase sent via email"
)
if rt == 'y':
print("say your key-phrase '" + messg + "'")
f_name1 = user_name + "test"
record_audio(f_name1, dir_test)
edit_txt(f_name1, test_file, prefix_test)
gmm_files = gmm_dir + user_name + ".gmm"
models = cpk.load(open(gmm_files, 'rb'))
file_paths_orig = open(enroll_file, 'r')
logsum = 0
log_likelihood_orig = np.zeros(1)
for path_orig in file_paths_orig:
path_orig = path_orig.strip()
print(path_orig)
(sro, audioo) = read(source_enroll + path_orig)
vector_o = extract_features(audioo, sro)
gmm = models # checking with each model one by one
scores = np.array(gmm.score(vector_o))
log_likelihood_orig[0] = scores.sum()
print(log_likelihood_orig[0])
logsum = logsum + log_likelihood_orig[0]
logavg = logsum / 5
print(logavg) # uncomment later
file_paths1 = open(test_file, 'r')
# Read the test directory and get the list of test audio files
for path1 in file_paths1:
print(path1[:-1])
path1 = path1[:-1]
(sr, audio) = read(source_test + path1)
vector = extract_features(audio, sr)
gmm = models # checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[0] = scores.sum()
print(log_likelihood[0]) #uncomment for reference
if ((logavg / log_likelihood[0]) * 100) > 85:
print("legit user")
else:
print("Invalid user")