def test_speaker_realtime(source):
modelpath = "C:\\Users\\USER\\GUI_SpeakerID\\speaker_models\\"
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.gmm')
]
#Load the Gaussian gender Models
models = [pickle.load(open(fname, 'rb')) for fname in gmm_files]
speakers = [fname.split("\\")[-1].split(".gmm")[0] for fname in gmm_files]
# Read the test directory and get the list of test audio files
rate, audio = read(source)
vector = extract_features(audio, rate)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
winner = np.argmax(log_likelihood)
print("\tdetected as -", speakers[winner])
time.sleep(1.0)
globals.speaker_realtime = speakers[winner]
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 gmm_graph(dir_path, file_name):
sr, audio = read(dir_path + file_name + ".wav")
vector = extract_features(audio, sr)
features = vector
model = GaussianMixture(n_components=16,
covariance_type='full',
n_init=3,
init_params='random',
random_state=0,
tol=1e-9,
max_iter=200)
features = np.array(features).reshape(-1, 1)
model.fit(features)
gmm_x = np.array(
np.linspace(np.min(features), np.max(features),
len(features))).reshape(-1, 1)
gmm_y = np.exp(model.score_samples(gmm_x))
fig, ax = plt.subplots()
ax.hist(features, bins=50, normed=True, alpha=0.5, color="#0070FF")
ax.plot(gmm_x,
gmm_y,
color="black",
lw=1,
label="Gaussian Mixture 1D Plot")
ax.set_ylabel("Probability density")
ax.set_xlabel("Arbitrary units")
plt.show()
def activity_detect():
print "activity detecting....."
global activities
#path to training data
modelpath = "activity_models/"
path = "record.wav"
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.pickle')
]
#Load the Gaussian gender Models
models = [cPickle.load(open(fname, 'r')) for fname in gmm_files]
speakers = [
fname.split("/")[-1].split(".pickle")[0] for fname in gmm_files
]
# Read the test directory and get the list of test audio files
path = path.strip()
sr, audio = read(path)
vector = extract_features(audio, sr)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
#print speakers,log_likelihood
winner = np.argmax(log_likelihood)
#print "\tdetected as - ", speakers[winner]
activities = speakers[winner]
def train(self, samples=3):
audio_paths = glob.glob(self.audio_path + '/*.wav')
count = 1
for path in audio_paths:
user = path.split('\\')[-1].split('_')[0]
print(user)
# Extracting features for each speaker (5 files per speakers)
features = np.asarray(())
print(path)
sr, audio = read(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))
if count == samples:
gmm = sklearn.mixture.GaussianMixture(n_components=16,
max_iter=200,
covariance_type='diag',
n_init=3)
gmm.fit(features)
# dumping the trained gaussian model
picklefile = os.path.join(self.audio_path,
user.split('.')[0] + ".gmm")
pickle.dump(gmm, open(picklefile, 'wb'))
print('modeling completed for speaker:', picklefile,
" with data point = ", features.shape)
features = np.asarray(())
count = 0
count = count + 1
def predictSpeaker(self):
file_paths = open(test_file, 'r')
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.gmm')
]
fname = os.path.join(modelpath, fname)
#Load the Gaussian gender Models
for fname in gmm_files:
models = [cPickle.load(open(fname)) for fname in gmm_files]
speakers = [
fname.split("\\")[-1].split(".gmm")[0] for fname in gmm_files
]
# Read the test directory and get the list of test audio files
for path in file_paths:
path = path.strip()
print path
sr, audio = read(source + path)
vector = extract_features(audio, sr)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
print log_likelihood[i]
winner = np.argmax(log_likelihood)
print "\tdetected as - ", speakers[winner]
def gmm_cluster_graph(dir_path, file_name):
sr, audio = read(dir_path+file_name+".wav")
vector = extract_features(audio, sr)
features = vector
model= GaussianMixture(n_components=16, covariance_type='diag',n_init=3, init_params='random', random_state=0, tol=1e-9, max_iter=200)
model.fit(features)
labels=model.predict(features)
plt.scatter(features[:,0], features[:,1], s=10, linewidth=1, cmap=plt.cm.get_cmap('tab20',16), c=labels)
plt.title("Gaussian Mixture Model")
plt.show()
def count():
print "speaker counting.........."
global speaker_name_len
global speaker_num
speaker_name_total = []
file_paths = []
num = filter_segment()
if num is 0:
peoplenum = 0
elif num is 1:
peoplenum = 1
else:
for i in range(num - 1): #舍弃最后一段
chunk_name = "chunk_wavs/chunk{0}.wav".format(i)
file_paths.append(chunk_name)
#path to speaker training data
modelpath = "speaker_models/"
#speaker gmm model
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.pickle')
]
#activity gmm model
models = [cPickle.load(open(fname, 'r')) for fname in gmm_files]
#speaker label
speakers = [
fname.split("/")[-1].split(".pickle")[0] for fname in gmm_files
]
# Read the test directory and get the list of test audio files
#人数及说话时长计算
for path in file_paths:
#print file_paths
path = path.strip()
sr, audio = read(path)
vector = extract_features(audio, sr)
#计算人数及说话时长
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
#print speakers,log_likelihood
winner = np.argmax(log_likelihood)
print "detected as - ", speakers[winner]
speaker_name_total.append(speakers[winner])
#delete repeat speaker
speaker_name = list(set(speaker_name_total))
for item in speaker_name:
speaker_len = speaker_name_total.count(item) * 3 #每个说话者的时长
speaker_num.append(speaker_len)
speaker_name_len.update({item: speaker_len}) #将说话者及说话者的长度存储成字典
print "speaker count done"
def chooseAction():
path = 'output.wav'
sr, audio = read(path)
vector = extract_features(audio, sr)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
winner = np.argmax(log_likelihood)
return speakers[winner]
def createModel(self, destination):
dest = destination
file_name = dest.split('/')
#print file_name
file_name = file_name[-2]
#print file_name
wav_files = [
f for f in os.listdir(Trainer.source) if f.endswith('.wav')
]
wavFileCount = len(wav_files)
count = 1
# Extracting features for each speaker (5 files per speakers)
features = np.asarray(())
for path in wav_files:
#path = path.strip()
#print path
# read the audio
sr, audio = read(Trainer.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 5 files of speaker are concatenated, then do model training
if count == wavFileCount:
gmm = GMM(n_components=16,
n_iter=200,
covariance_type='diag',
n_init=3)
gmm.fit(features)
# dumping the trained gaussian model
picklefile = file_name + ".gmm"
#print picklefile
cPickle.dump(gmm, open(dest + picklefile, 'w'))
#dest = dest.split('/')
dest = '/'.join((dest.split('/'))[-3:-1])
with open(r"C:\VOrder\sys\speaker_model\training_models.txt",
"a") as myfile:
myfile.write(dest + '/' + picklefile + '\n')
for file in wav_files:
os.remove(Trainer.source + file)
print 'modeling completed for speaker:', file_name
speech.say('modeling completed for speaker:' + file_name)
features = np.asarray(())
count = 0
count = count + 1
def predict(self, test_path):
sr, audio = read(test_path)
vector = extract_features(audio, sr)
gmms = glob.glob(os.path.join(self.audio_path, '*.gmm'))
#print(gmms)
scores = []
for i in gmms:
#print(i)
user = pickle.load(open(i, 'rb'))
scores.append(
(i.split('\\')[-1].split('.')[0], user.score(vector)))
#print(scores)
print(scores)
return sorted(scores, key=lambda x: x[1], reverse=True)[0][0]
def load_test_audios(test_audio_dir: str):
"""
Extracts the features from the test files
Args:
test_audio_dir: Path to the directory in which the test audios are stored
Returns
vectors (list): List of features vectors, one for each audio
"""
audio_tests = os.listdir(os.path.join(test_audio_dir))
vectors = []
for file in audio_tests:
sr, audio = read(os.path.join(test_audio_dir, file))
vector = extract_features(audio, sr)
vectors.append((file.split('.')[0], vector))
return vectors
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")
def count():
global speaker_name_len
global speaker_num
speaker_name_total = []
file_paths = []
num = filter_segment()
if num is 0:
peoplenum = 0
elif num is 1:
peoplenum = 1
else:
for i in range(num - 1): #舍弃最后一段
chunk_name = "chunk_wavs/chunk{0}.wav".format(i)
file_paths.append(chunk_name)
modelpath = "speaker_models/" #說話者模型的路徑
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.pickle')
] #讀取訓練好的gmm文件
models = [cPickle.load(open(fname, 'r'))
for fname in gmm_files] #讀取每個gmm文件的內容
speakers = [
fname.split("/")[-1].split(".pickle")[0] for fname in gmm_files
] #讀取說話者標籤
#人数及说话时长计算
speaker_num = []
for path in file_paths:
#print file_paths
path = path.strip()
sr, audio = read(path)
vector = extract_features(audio, sr)
#计算人数及说话时长
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
#print speakers,log_likelihood
winner = np.argmax(log_likelihood)
print "detected as - ", speakers[winner]
speaker_name_total.append(speakers[winner])
#delete repeat speaker
speaker_name = list(set(speaker_name_total))
for item in speaker_name:
speaker_len = speaker_name_total.count(item) * 3 #每個說話者的長度
speaker_num.append(speaker_len)
def train_models():
#path to training data
source = "C:\\Users\\USER\\GUI_SpeakerID\\development_set\\"
#path where training speakers will be saved
dest = "C:\\Users\\USER\\GUI_SpeakerID\\speaker_models\\"
train_file = "voice_list_enroll.txt"
file_paths = open(train_file, 'rb')
count = 1
# Extracting features for each speaker (5 files per speakers)
features = np.asarray(())
for path in file_paths:
path = path.strip()
print(path)
# read the audio
rate, audio = read(source + path.decode('utf-8'))
# extract 40 dimensional MFCC & delta MFCC features
vector = extract_features(audio, rate)
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 = GaussianMixture(n_components=16,
max_iter=200,
covariance_type='diag',
n_init=3)
gmm.fit(features)
# dumping the trained gaussian model
picklefile = path.decode().split("_")[0] + ".gmm"
pickle.dump(gmm, open(dest + picklefile, 'wb+'))
print('+ modeling completed for speaker:', picklefile,
" with data point = ", features.shape)
features = np.asarray(())
count = 0
else:
count = count + 1
def send_credential(self):
print("in send credential..", self.ids["b2"].disabled)
#self.ids.entry.text="Speak your Id no"
self.ids["b1"].disabled = True
getaudio.fun("audio.wav")
#feature_extraction.fun("audio.wav","data")
#idno1=getid.fun(feature_extraction.fun("audio.wav"))
#got_idno=idno1
#print(got_idno)
modelpath = "speaker_models/"
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.gmm')
]
models = [pickle.load(open(fname, 'rb')) for fname in gmm_files]
speakers = [
fname.split("\\")[-1].split(".gmm")[0] for fname in gmm_files
]
audio, sr = librosa.load("audio.wav", res_type='kaiser_fast')
vector = extract_features(audio, sr)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
print("score : ", scores.sum())
winner = np.argmax(log_likelihood)
print(winner)
print("\tdetected as - ", speakers[winner])
if speakers[winner] == "speaker_models/sid":
u = "http://localhost:5000/attendence?year=" + year + "&branch=" + branch + "&sem=" + sem + "&id_no=" + id_no
r = requests.post(url=u)
print(r.text)
self.ids.entry.text = r.text
self.ids.entry.text = "sid"
else:
self.ids.entry.text = "you are not id_no : " + id_no
self.ids.entry.text = "Not sid"
self.ids["b1"].disabled = False
self.ids["b2"].disabled = False
def func(file):
#path to training data
source = cwd + "/development_set/"
modelpath = cwd + "/speaker_models/"
test_file = "4.txt"
with open(test_file, "w") as f:
f.write(file)
file_paths = open(test_file, 'r')
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.gmm')
]
#Load the Gaussian gender Models
models = [pickle.load(open(fname, 'rb')) for fname in gmm_files]
speakers = [fname.split("\\")[-1].split(".gmm")[0] for fname in gmm_files]
# Read the test directory and get the list of test audio files
for path in file_paths:
path = path.strip()
print(path)
sr, audio = read(source + path)
vector = extract_features(audio, sr)
log_likelihood = np.zeros(len(models))
#l_score=[]
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
max_score = np.amax(scores)
log_likelihood[i] = scores.sum()
#l_score[i].append(scores)
#candidate_probability = (np.exp(candidate_score)/np.exp(max_score)) * 100
winner = np.argmax(log_likelihood)
print("\tdetected as - ", speakers[winner])
#print("Score of ->> ",candidate_probability)
time.sleep(1.0)
return speakers[winner]
def predict_voice(path):
modelpath = "new_speaker_model/"
gmm_files = [os.path.join(modelpath,fname) for fname in
os.listdir(modelpath) if fname.endswith('.gmm')]
models = [cPickle.load(open(fname,'rb')) for fname in gmm_files]
speakers = [fname.split("/")[-1].split(".gmm")[0] for fname
in gmm_files]
print(path)
sr,audio = read(path)
vector = extract_features(audio,sr)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
winner = np.argmax(log_likelihood)
print("\tdetected as - ", speakers[winner])
return speakers[winner]
def test_speaker():
#path to training data
source = "C:\\Users\\USER\\GUI_SpeakerID\\development_set\\"
modelpath = "C:\\Users\\USER\\GUI_SpeakerID\\speaker_models\\"
test_file = "voice_list_test.txt"
file_paths = open(test_file,'rb')
gmm_files = [os.path.join(modelpath,fname) for fname in
os.listdir(modelpath) if fname.endswith('.gmm')]
#Load the Gaussian gender Models
models = [pickle.load(open(fname,'rb')) for fname in gmm_files]
speakers = [fname.split("\\")[-1].split(".gmm")[0] for fname
in gmm_files]
# Read the test directory and get the list of test audio files
for path in file_paths:
path = path.strip()
print (path)
rate,audio = read(source + path.decode('utf-8'))
vector = extract_features(audio,rate)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
winner = np.argmax(log_likelihood)
print ("\tdetected as -", speakers[winner])
time.sleep(1.0)
globals.speaker = speakers[winner]
def speakerName():
#path to training data
source = "development_set\\"
modelpath = "speaker_models\\"
test_file = "development_set_test.txt"
file_paths = open(test_file, 'r')
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.gmm')
]
#Load the Gaussian gender Models
models = [cPickle.load(open(fname, 'rb')) for fname in gmm_files]
speakers = [fname.split("\\")[-1].split(".gmm")[0] for fname in gmm_files]
# Read the test directory and get the list of test audio files
sr, audio = read("file.wav")
vector = extract_features(audio, sr)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
winner = np.argmax(log_likelihood)
#print (log_likelihood[winner],'\n')
#print(winner)
print("\tDetected as - ", speakers[winner])
return speakers[winner]
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")
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 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
inputFile(train_file, source, train_num)
file_paths = open(train_file, 'r')
count = 1
# Extracting features for each speaker (13 files per speakers)
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 1 files of speaker are concatenated, then do model training
if count == 13:
gmm = GaussianMixture(
n_components=16, covariance_type='diag', n_init=3
) #n_components = the number of mixture components, n_init = initialization
gmm.fit(features) #추출된 특징들 토대로 EM 알고리즘을 통해 모델 파라미터 측정
# dumping the trained gaussian model
picklefile = path.split(".wav")[0] + ".gmm"
def run():
source = "test/"
modelpath = "models/"
test_file = "test.txt"
file_paths = open(test_file, 'r')
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.gmm')
]
models = []
for i in range(len(gmm_files)):
file = open(gmm_files[i], 'rb')
models.insert(i, cPickle.load(file))
speakers = [fname.split("/")[-1].split(".gmm")[0] for fname in gmm_files]
# Read the test directory and get the list of test audio files
print("Start. ")
last = []
while True:
test = CreateRecord.Record()
test.createRecord("test.wav")
path = "test.wav"
sr, audio = read(path)
vector = extract_features(audio, sr)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i]
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
winner = np.argmax(log_likelihood)
if speakers[winner] == "motrinhduyet":
webbrowser.get(
"C:/Program Files (x86)/Internet Explorer/iexplore.exe %s"
).open("http://Google.com.vn")
break
elif speakers[winner] == "excel":
os.startfile(
'C:/Program Files (x86)/Microsoft Office/root/Office16/EXCEL.EXE'
)
break
elif speakers[winner] == "khoamanhinh":
ctypes.windll.user32.LockWorkStation()
break
# elif speakers[winner] == "tatnguon":
# os.system("shutdown /s /t 3600")
# break
elif speakers[winner] == "24h":
webbrowser.get(
"C:/Program Files (x86)/Internet Explorer/iexplore.exe %s"
).open("http://24h.com.vn")
break
elif speakers[winner] == "dung":
break
