def predict(self, signal, fs):
# remove silence
signal = remove_silence(fs, signal)
# signal = StandardScaler().fit_transform(signal)
# Extract feature
mfcc_feat = mfcc(signal, fs)
if self.is_delta:
mfcc_feat = delta(mfcc_feat, 2)
return self.NN.predict(mfcc_feat)
def train(self):
self.message = "Training result:"
# File path
wavpath = self.filepath + "/wav"
if self.verbose:
print("Wav files from: " + wavpath)
# List all the filenames of wav directory
wav_files = [f for f in os.listdir(wavpath) if f.endswith('.wav')]
n = len(wav_files)
if (n < 1):
assert ("No wav files found at " + wavpath +
". Cancelling operation")
return
features = None
target = None
is_firstrun = True
row = 0
col = 0
userList = open(self.filepath + "/metadata.txt", "w")
wav_dic = {}
# Loop until all files are converted to csv
for audio in wav_files:
fs, signal = wavfile.read(wavpath + "/" + audio)
# remove silence
signal = remove_silence(fs, signal)
# Extract features from audio signal
mfcc_feat = mfcc(signal, fs)
if self.is_delta:
mfcc_feat = delta(mfcc_feat, 2)
# save feature as csv files for debugging
np.savetxt(self.filepath + "/csv/" + audio[7:-4] + ".csv",
mfcc_feat,
fmt='%.8f',
delimiter=',')
# If user is not already in the list/dictionary add them
try:
wav_dic[audio[0:-6]]
except:
userList.write(audio[0:-6] + "\n")
wav_dic[audio[0:-6]] = col
col += 1
if self.verbose:
print("\nFile:", audio)
print("Feature: ", mfcc_feat.shape)
if is_firstrun:
features = mfcc_feat
target = [0] * mfcc_feat.shape[0]
for i in range(mfcc_feat.shape[0]):
target[row] = wav_dic[audio[0:-6]]
row += 1
is_firstrun = False
else:
features = np.vstack((features, mfcc_feat))
for i in range(mfcc_feat.shape[0]):
target = np.append(target, [wav_dic[audio[0:-6]]])
row += 1
# userList.write("Anonymous")
userList.close()
# Load user names
userList = open(self.filepath + "/metadata.txt", "r")
self.users = userList.read().split("\n")[:-1]
userList.close()
features = features.astype(np.float)
if self.verbose:
print_label("Data sets", character="-")
print("Features:", features.shape)
print(features)
print("\nTarget:", target.shape)
print(target)
print_label("Neural Network modelling", character="-")
print("Modelling started, this may take a while")
# Features and target are made now train them
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(features,
target,
test_size=0.33,
random_state=42)
self.mlp.fit(X_train, y_train)
self.message += "\nTotal iteration run: %d" % self.mlp.n_iter_
predictions = self.mlp.predict(X_test)
from sklearn.metrics import classification_report, confusion_matrix
self.message += "\n"
self.message += classification_report(y_test,
predictions,
target_names=self.users)
self.message += "\nconfusion_matrix\n"
self.message += np.array_str(confusion_matrix(y_test, predictions))
# Training is now complete, save the model
pickle.dump(self.mlp, open(self.filepath + '/model.pkl', 'wb'))
self.message += "\nModel is saved to %s/model.pkl" % self.filepath
if self.verbose:
print(self.message)
# Load files
self.NN = pickle.load(open(self.filepath + '/model.pkl', 'rb'))
# Load user names
userList = open(self.filepath + "/metadata.txt", "r")
self.users = userList.read().split('\n')
userList.close()
return self.message