emotion_sample.py

import librosa
import soundfile
import os, glob, pickle
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import accuracy_score

# Extract features (mfcc, chroma, mel) from a sound file
# Core part, VVIP function for emotional detector
def extract_feature(file_name, mfcc, chroma, mel):
    with soundfile.SoundFile(file_name) as sound_file:
        X = sound_file.read(dtype='float32')
        sample_rate = sound_file.samplerate
        if chroma:
            stft = np.abs(librosa.stft(X))
        result = np.array([])
        if mfcc:
            mfcc = np.mean(librosa.feature.mfcc(y = X, sr = sample_rate, n_mfcc = 40).T, axis = 0)
            result = np.hstack((result, mfcc)) # stacks arrays in sequence horizontally(in a columnar fashion)
        if chroma:
            chroma = np.mean(librosa.feature.chroma_stft(S=stft, sr = sample_rate).T, axis = 0)
            result = np.hstack((result, chroma))
        if mel:
            mel = np.mean(librosa.feature.melspectrogram(X, sr = sample_rate).T, axis = 0)
            result = np.hstack((result, mel))
        return result

# Load the data and extract features for each sound file
def load_data(emotions, observed_emotions, test_size = 0.2):
    x, y = [], []
    for file in glob.glob('/home/deokgyu.ahn/practice/Resource/Code/emotion/duck_emotion/ravdess_data/Actor_*/*.wav'):
        file_name = os.path.basename(file)
        emotion = emotions[file_name.split("-")[2]]
        if emotion not in observed_emotions:
            continue
        feature = extract_feature(file, mfcc=True, chroma=True, mel=True)
        x.append(feature)
        y.append(emotion)
    return train_test_split(np.array(x), y, test_size=test_size, random_state=9)

        

def main():
    # Emotions in the RAVDESS dataset
    emotions = {
            '01' : 'neutral',
            '02' : 'calm',
            '03' : 'happy',
            '04' : 'sad',
            '05' : 'angry',
            '06' : 'fearful',
            '07' : 'disgust', 
            '08' : 'surprised',
    }			

    observed_emotions = ['neutral', 'angry']

    # Split the dataset
    x_train, x_test, y_train, y_test = load_data(emotions, observed_emotions, test_size = 0.25)
    
    # Get the shape of the training and testing datasets
    print((x_train.shape[0], x_test.shape[0]))

    print(f'Features extracted: {x_train.shape[1]}')

    #initialize the Multi Layer Perceptron Classifier
    model = MLPClassifier(alpha = 0.01, batch_size = 256, epsilon= 1e-08,
    hidden_layer_sizes = (300, ), learning_rate = 'adaptive', max_iter=500)
    
    # Duck's note : If you want to increase the accuracy, make this network deeper
    # Rather than using crude MLPClssifier

    # Train the model
    model.fit(x_train, y_train)

    # Predict for the test set
    y_pred=model.predict(x_test)

    # Calculate the accuracy of our model
    accuracy = accuracy_score(y_true=y_test, y_pred=y_pred)

    # Print the accuracy
    print("Accuracy: {:.2f}%".format(accuracy*100))



if __name__ == "__main__":

    main()