Feature extraction section for simple audio classifier blogpost

feature_extraction.py

import glob
import os
import librosa
import numpy as np
import pandas as pd
from scipy.stats import kurtosis, skew


featureVectorLength = 140  # n_mfcc * number_of_summary_statistics


def extract_features_from_file(file_name):
    raw_sound, sample_rate = librosa.load(file_name)

    # one row per extracted coefficient, one column per frame
    mfccs = librosa.feature.mfcc(y=raw_sound, sr=sample_rate, n_mfcc=20)

    mfccs_min = np.min(mfccs, axis=1)  # row-wise summaries
    mfccs_max = np.max(mfccs, axis=1)
    mfccs_median = np.median(mfccs, axis=1)
    mfccs_mean = np.mean(mfccs, axis=1)
    mfccs_variance = np.var(mfccs, axis=1)
    mfccs_skeweness = skew(mfccs, axis=1)
    mfccs_kurtosis = kurtosis(mfccs, axis=1)

    return mfccs_min, mfccs_max, mfccs_median, mfccs_mean, mfccs_variance, mfccs_skeweness, mfccs_kurtosis


def extract_features_from_directories(parent_dir, sub_dirs, file_ext="*.wav"):
    """
    Processes all the files in the subdirectories located in the parent directory. For each file in the subdirectories
    with the correct extension, it extracts the feature vector and stores it into the feature matrix. The labels
    are inferred from the file names.
    :param parent_dir: Parent directory that contains the sub directories..
    :param sub_dirs: Subdirectories whose files will be processed
    :param file_ext: File extension of the files which will be processed.
    :return: A pair. The feature matrix (each row is a feature vector, each column a feature), and the
    corresponding labels for each row of the matrix.
    """
    feature_matrix, labels = np.empty((0, featureVectorLength)), np.empty(0)

    for label, sub_dir in enumerate(sub_dirs):
        for fn in glob.glob(os.path.join(parent_dir, sub_dir, file_ext)):
            try:
                mfccs_min, mfccs_max, mfccs_median, mfccs_mean, mfccs_variance, mfccs_skeweness, mfccs_kurtosis = extract_features_from_file(fn)
                print("Finished processing file: ", fn)
            except Exception as e:
                print("Error while processing file: ", fn)
                continue

            # concatenate extracted features
            new_feature_vector = np.hstack([mfccs_min, mfccs_max, mfccs_median, mfccs_mean, mfccs_variance, mfccs_skeweness, mfccs_kurtosis])

            # add current feature vector as last row in feature matrix
            feature_matrix = np.vstack([feature_matrix, new_feature_vector])

            # extracts label from the file name. Change '\\' to  '/' on Unix systems
            labels = np.append(labels, fn.split('\\')[2].split('-')[1])

    return np.array(feature_matrix), np.array(labels, dtype=np.int)


def prepare_features(training_dirs, validation_dirs, training_name, validation_name):
    """
    Extracts and stores features and labels as a pandas dataframe and series, respectively.
    :return: Nothing. Just stores the features and labels as files.
    """

    parent_dir = 'Sound-Data'  # name of the directory which contains the recordings
    training_sub_dirs = training_dirs
    validation_sub_dirs = validation_dirs

    # ndarrays
    training_features, training_labels = extract_features_from_directories(parent_dir, training_sub_dirs)
    test_features, test_labels = extract_features_from_directories(parent_dir, validation_sub_dirs)

    # convert ndarray to pandas dataframe
    training_examples = pd.DataFrame(training_features, columns=list(range(1, featureVectorLength+1)))
    # convert ndarray to pandas series
    training_labels = pd.Series(training_labels.tolist())

    # convert ndarray to pandas dataframe
    validation_examples = pd.DataFrame(test_features, columns=list(range(1, featureVectorLength+1)))
    # convert ndarray to pandas series
    validation_labels = pd.Series(test_labels.tolist())

    # store extracted training data
    training_examples.to_pickle('Extracted_Features\\' + training_name + '_features.pkl')
    training_labels.to_pickle('Extracted_Features\\' + training_name + '_labels.pkl')

    # store extracted validation data
    validation_examples.to_pickle('Extracted_Features\\' + validation_name + '_features.pkl')
    validation_labels.to_pickle('Extracted_Features\\' + validation_name + '_labels.pkl')


# First 9 folds will be used for training, the tenth for validation.
training_dirs = ["fold1", "fold2", "fold3", "fold4", "fold5", "fold6", "fold7", "fold8", "fold9"]
validation_dirs = ["fold10"]
# prepare_features(training_dirs, validation_dirs, 'notFold10', 'fold10')

# Read the stored features and labels:
# print(pd.read_pickle('Extracted_Features\\fold10_features.pkl'))
# print(pd.read_pickle('Extracted_Features\\fold10_labels.pkl'))


def visualize_data(file_name):
    # Example of how to extract features and obtain the final feature vector from a given audio file:

    # First we load the audio file.
    raw_sound, sample_rate = librosa.load(file_name)  # file must be in the root folder of your project

    print("raw_sound:", raw_sound)
    print("raw_sound.shape:", raw_sound.shape)
    print("\n")

    mfccs = librosa.feature.mfcc(y=raw_sound, sr=sample_rate, n_mfcc=20)  # compute the MFCC matrix

    # Next we compute the summary statistics, each of them summarizes the MFCC matrix in its own way.
    mfccs_min = np.min(mfccs, axis=1)  # row-wise minimum, etc
    mfccs_max = np.max(mfccs, axis=1)
    mfccs_median = np.median(mfccs, axis=1)
    mfccs_mean = np.mean(mfccs, axis=1)
    mfccs_variance = np.var(mfccs, axis=1)
    mfccs_skeweness = skew(mfccs, axis=1)
    mfccs_kurtosis = kurtosis(mfccs, axis=1)

    # We obtain the feature vector by concatenating the different summaries.
    finalFeatureVector = np.concatenate([mfccs_min, mfccs_max, mfccs_median, mfccs_mean, mfccs_variance, mfccs_skeweness, mfccs_kurtosis])

    print("mfccs:", mfccs)
    print("mfccs.shape:", mfccs.shape)
    print("\n")

    print("mfccs_min:", mfccs_min)
    print("mfccs_min.shape:", mfccs_min.shape)
    print("\n")

    print("mfccs_max:", mfccs_max)
    print("mfccs_max.shape:", mfccs_max.shape)
    print("\n")

    print("mfccs_median:", mfccs_median)
    print("mfccs_median.shape:", mfccs_median.shape)
    print("\n")

    print("mfccs_mean:", mfccs_mean)
    print("mfccs_mean.shape:", mfccs_mean.shape)
    print("\n")

    print("mfccs_variance:", mfccs_variance)
    print("mfccs_variance.shape:", mfccs_variance.shape)
    print("\n")

    print("mfccs_skeweness:", mfccs_skeweness)
    print("mfccs_skeweness.shape:", mfccs_skeweness.shape)
    print("\n")

    print("mfccs_kurtosis:", mfccs_kurtosis)
    print("mfccs_kurtosis.shape:", mfccs_kurtosis.shape)
    print("\n")

    print("finalFeatureVector", finalFeatureVector)
    print("finalFeatureVector.shape:", finalFeatureVector.shape)


# visualize_data("24074-1-0-3.wav")  # file must be in the project's root folder