J

FeaturesExtractor.py

@@ -0,0 +1,52 @@
+import numpy as np
+from sklearn import preprocessing
+from scipy.io.wavfile import read
+from python_speech_features import mfcc
+from python_speech_features import delta
+
+
+class FeaturesExtractor:
+    def __init__(self):
+        pass
+       
+    def extract_features(self, audio_path):
+        """
+        Extract voice features including the Mel Frequency Cepstral Coefficient (MFCC)
+        from an audio using the python_speech_features module, performs Cepstral Mean
+        Normalization (CMS) and combine it with MFCC deltas and the MFCC double
+        deltas.
+     
+        Args: 	    
+            audio_path (str) : path to wave file without silent moments. 
+        Returns: 	    
+            (array) : Extracted features matrix. 	
+        """
+        rate, audio  = read(audio_path)
+        mfcc_feature = mfcc(# The audio signal from which to compute features.
+                            audio,
+                            # The samplerate of the signal we are working with.
+                            rate,
+                            # The length of the analysis window in seconds. 
+                            # Default is 0.025s (25 milliseconds)
+                            winlen       = 0.05,
+                            # The step between successive windows in seconds. 
+                            # Default is 0.01s (10 milliseconds)
+                            winstep      = 0.01,
+                            # The number of cepstrum to return. 
+                            # Default 13.
+                            numcep       = 5,
+                            # The number of filters in the filterbank.
+                            # Default is 26.
+                            nfilt        = 30,
+                            # The FFT size. Default is 512.
+                            nfft         = 512,
+                            # If true, the zeroth cepstral coefficient is replaced 
+                            # with the log of the total frame energy.
+                            appendEnergy = True)
+    
+        
+        mfcc_feature  = preprocessing.scale(mfcc_feature)
+        deltas        = delta(mfcc_feature, 2)
+        double_deltas = delta(deltas, 2)
+        combined      = np.hstack((mfcc_feature, deltas, double_deltas))
+        return combined

det.py

@@ -0,0 +1,68 @@
+import os
+import pickle
+import warnings
+import numpy as np
+from FeaturesExtractor import FeaturesExtractor
+
+warnings.filterwarnings("ignore")
+
+
+class GenderIdentifier:
+
+    def __init__(self, females_files_path, males_files_path, females_model_path, males_model_path):
+        self.females_training_path = females_files_path
+        self.males_training_path   = males_files_path
+        self.error                 = 0
+        self.total_sample          = 0
+        self.features_extractor    = FeaturesExtractor()
+        # load models
+        self.females_gmm = pickle.load(open(females_model_path, 'rb'))
+        self.males_gmm   = pickle.load(open(males_model_path, 'rb'))
+
+    def process(self):
+        files = self.get_file_paths(self.females_training_path, self.males_training_path)
+        # read the test directory and get the list of test audio files
+        for file in files:
+            self.total_sample += 1
+            print("%10s %8s %1s" % ("--> TESTING", ":", os.path.basename(file)))
+
+            vector = self.features_extractor.extract_features(file)
+            winner = self.identify_gender(vector)
+            expected_gender = file.split("/")[1][:-1]
+
+            print("%10s %6s %1s" % ("+ EXPECTATION",":", expected_gender))
+            print("%10s %3s %1s" %  ("+ IDENTIFICATION", ":", winner))
+
+            if winner != expected_gender: self.error += 1
+            print("----------------------------------------------------")
+
+        accuracy     = ( float(self.total_sample - self.error) / float(self.total_sample) ) * 100
+        accuracy_msg = "*** Accuracy = " + str(round(accuracy, 3)) + "% ***"
+        print(accuracy_msg)
+
+    def get_file_paths(self, females_training_path, males_training_path):
+        # get file paths
+        females = [ os.path.join(females_training_path, f) for f in os.listdir(females_training_path) ]
+        males   = [ os.path.join(males_training_path, f) for f in os.listdir(males_training_path) ]
+        files   = females + males
+        return files
+
+    def identify_gender(self, vector):
+        # female hypothesis scoring
+        is_female_scores         = np.array(self.females_gmm.score(vector))
+        is_female_log_likelihood = is_female_scores.sum()
+        # male hypothesis scoring
+        is_male_scores         = np.array(self.males_gmm.score(vector))
+        is_male_log_likelihood = is_male_scores.sum()
+
+        print("%10s %5s %1s" % ("+ FEMALE SCORE",":", str(round(is_female_log_likelihood, 3))))
+        print("%10s %7s %1s" % ("+ MALE SCORE", ":", str(round(is_male_log_likelihood,3))))
+
+        if is_male_log_likelihood > is_female_log_likelihood: winner = "male"
+        else                                                : winner = "female"
+        return winner
+
+
+if __name__== "__main__":
+    gender_identifier = GenderIdentifier("TestingData/females", "TestingData/males", "females.gmm", "males.gmm")
+    gender_identifier.process()

modeltrainer.py

@@ -0,0 +1,76 @@
+import os
+import pickle
+import warnings
+import numpy as np
+from sklearn.mixture import GMM
+from FeaturesExtractor import FeaturesExtractor
+
+warnings.filterwarnings("ignore")
+
+
+class ModelsTrainer:
+
+    def __init__(self, females_files_path, males_files_path):
+        self.females_training_path = females_files_path
+        self.males_training_path   = males_files_path
+        self.features_extractor    = FeaturesExtractor()
+
+    def process(self):
+        females, males = self.get_file_paths(self.females_training_path,
+                                             self.males_training_path)
+        # collect voice features
+        female_voice_features = self.collect_features(females)
+        male_voice_features   = self.collect_features(males)
+        # generate gaussian mixture models
+        females_gmm = GMM(n_components = 16, n_iter = 200, covariance_type='diag', n_init = 3)
+        males_gmm   = GMM(n_components = 16, n_iter = 200, covariance_type='diag', n_init = 3)
+        # fit features to models
+        females_gmm.fit(female_voice_features)
+        males_gmm.fit(male_voice_features)
+        # save models
+        self.save_gmm(females_gmm, "females")
+        self.save_gmm(males_gmm,   "males")
+
+    def get_file_paths(self, females_training_path, males_training_path):
+        # get file paths
+        females = [ os.path.join(females_training_path, f) for f in os.listdir(females_training_path) ]
+        males   = [ os.path.join(males_training_path, f) for f in os.listdir(males_training_path) ]
+        return females, males
+
+    def collect_features(self, files):
+        """
+    	Collect voice features from various speakers of the same gender.
+
+    	Args:
+    	    files (list) : List of voice file paths.
+
+    	Returns:
+    	    (array) : Extracted features matrix.
+    	"""
+        features = np.asarray(())
+        # extract features for each speaker
+        for file in files:
+            print("%5s %10s" % ("PROCESSNG ", file))
+            # extract MFCC & delta MFCC features from audio
+            vector    = self.features_extractor.extract_features(file)
+            # stack the features
+            if features.size == 0:  features = vector
+            else:                   features = np.vstack((features, vector))
+        return features
+
+    def save_gmm(self, gmm, name):
+        """ Save Gaussian mixture model using pickle.
+
+            Args:
+                gmm        : Gaussian mixture model.
+                name (str) : File name.
+        """
+        filename = name + ".gmm"
+        with open(filename, 'wb') as gmm_file:
+            pickle.dump(gmm, gmm_file)
+        print ("%5s %10s" % ("SAVING", filename,))
+
+
+if __name__== "__main__":
+    models_trainer = ModelsTrainer("TrainingData/females", "TrainingData/males")
+    models_trainer.process()