See an explanation of the Mel Frequency Cepstral Coefficient
There are various Python libs dealing with speech features (Speech Features, SpeechRecognition)
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
import os import argparse import numpy as np from scipy.io import wavfile from hmmlearn import hmm from features import mfcc # Function to parse input arguments def build_arg_parser(): parser = argparse.ArgumentParser(description='Trains the HMM classifier') parser.add_argument("--input-folder", dest="input_folder", required=True, help="Input folder containing the audio files in subfolders") return parser # Class to handle all HMM related processing class HMMTrainer(object): def __init__(self, model_name='GaussianHMM', n_components=4, cov_type='diag', n_iter=1000): self.model_name = model_name self.n_components = n_components self.cov_type = cov_type self.n_iter = n_iter self.models = [] if self.model_name == 'GaussianHMM': self.model = hmm.GaussianHMM(n_components=self.n_components, covariance_type=self.cov_type, n_iter=self.n_iter) else: raise TypeError('Invalid model type') # X is a 2D numpy array where each row is 13D def train(self, X): np.seterr(all='ignore') self.models.append(self.model.fit(X)) # Run the model on input data def get_score(self, input_data): return self.model.score(input_data) if __name__=='__main__': args = build_arg_parser().parse_args() input_folder = args.input_folder hmm_models = [] # Parse the input directory for dirname in os.listdir(input_folder): # Get the name of the subfolder subfolder = os.path.join(input_folder, dirname) if not os.path.isdir(subfolder): continue # Extract the label label = subfolder[subfolder.rfind('/') + 1:] # Initialize variables X = np.array([]) y_words = [] # Iterate through the audio files (leaving 1 file for testing in each class) for filename in [x for x in os.listdir(subfolder) if x.endswith('.wav')][:-1]: # Read the input file filepath = os.path.join(subfolder, filename) sampling_freq, audio = wavfile.read(filepath) # Extract MFCC features mfcc_features = mfcc(audio, sampling_freq) # Append to the variable X if len(X) == 0: X = mfcc_features else: X = np.append(X, mfcc_features, axis=0) # Append the label y_words.append(label) print('X.shape =', X.shape) # Train and save HMM model hmm_trainer = HMMTrainer() hmm_trainer.train(X) hmm_models.append((hmm_trainer, label)) hmm_trainer = None # Test files input_files = [ 'one.wav', 'two.wav', 'three.wav', 'four.wav' ] # Classify input data for input_file in input_files: # Read input file sampling_freq, audio = wavfile.read(input_file) # Extract MFCC features mfcc_features = mfcc(audio, sampling_freq) # Define variables max_score = None output_label = None # Iterate through all HMM models and pick # the one with the highest score for item in hmm_models: hmm_model, label = item score = hmm_model.get_score(mfcc_features) if score > max_score: max_score = score output_label = label # Print the output print("\nTrue:", input_file[input_file.find('/')+1:input_file.rfind('/')]) print("Predicted:", output_label) |
