utils.py

import librosa
import numpy as np
import matplotlib
# Force matplotlib to not use any Xwindows backend.
matplotlib.use('Agg')

from matplotlib.pyplot import specgram
import matplotlib.pyplot as plt
import sys



def load_sound_files(file_paths):
    raw_sounds = []
    for fp in file_paths:
        X,sr = librosa.load(fp, sr=44100)
        raw_sounds.append(X)
    return raw_sounds

def plot_waves(sound_names,raw_sounds):
    i = 1
    fig = plt.figure(figsize=(25,90), dpi = 900)
    for n,f in zip(sound_names,raw_sounds):
        plt.subplot(10,1,i)
        librosa.display.waveplot(np.array(f),sr=44100)
        plt.title(n.title())
        i += 1
    plt.suptitle('Figure 1: Waveplot',x=0.5, y=0.915,fontsize=18)
    plt.show()
    
def plot_specgram(sound_names,raw_sounds):
    i = 1
    fig = plt.figure(figsize=(25,90), dpi = 900)
    for n,f in zip(sound_names,raw_sounds):
        plt.subplot(10,1,i)
        specgram(np.array(f), Fs=44100)
        plt.title(n.title())
        i += 1
    plt.suptitle('Figure 2: Spectrogram',x=0.5, y=0.915,fontsize=18)
    plt.show()


    
def plot_log_power_specgram(sound_names,raw_sounds):
    i = 1
    fig = plt.figure(figsize=(25,90), dpi = 900)
    for n,f in zip(sound_names,raw_sounds):
        plt.subplot(10,1,i)
        D = librosa.logamplitude(np.abs(librosa.stft(f))**2, ref_power=np.max)
        librosa.display.specshow(D,x_axis='time' ,y_axis='log')
        plt.title(n.title())
        i += 1
    plt.suptitle('Figure 3: Log power spectrogram',x=0.5, y=0.915,fontsize=18)
    plt.show()
    
    
    
def specgram_frombuffer(raw_sound, dimx, dimy, fname='', fs=44100, show=False, dpi=900):
    """ fs  is the frequency sampling rate of the audio file. It has nothing to do with plotted samples
        
    """
    
    fig = plt.figure(figsize=(dimy,dimx), dpi = dpi)
    
    plt.subplot(3,1,1)
    specgram(np.array(raw_sound), Fs=fs)
    plt.axis('off')
    
    #ax = plt.Axes(fig, [0., 0., 1., 1.])
    #ax.set_axis_off()
    
    if not len(fname):
        filename = './data/unnamed.png'
    else:
        filename = fname
    
    plt.tight_layout()
    plt.savefig(filename, bbox_inches='tight', pad_inches = 0)
    
    if show:
        plt.show()
        
    
    plt.close(fig)
    
    
    
def extract_feature(file_name):
    X, sample_rate = librosa.load(file_name)
    stft = np.abs(librosa.stft(X))
    mfccs = np.mean(librosa.feature.mfcc(y=X, sr=sample_rate, n_mfcc=40).T,axis=0)
    chroma = np.mean(librosa.feature.chroma_stft(S=stft, sr=sample_rate).T,axis=0)
    mel = np.mean(librosa.feature.melspectrogram(X, sr=sample_rate).T,axis=0)
    contrast = np.mean(librosa.feature.spectral_contrast(S=stft, sr=sample_rate).T,axis=0)
    tonnetz = np.mean(librosa.feature.tonnetz(y=librosa.effects.harmonic(X), sr=sample_rate).T,axis=0)
    return mfccs,chroma,mel,contrast,tonnetz

def parse_audio_files(parent_dir,sub_dirs,file_ext='*.wav'):
    features, labels = np.empty((0,193)), 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)):
            mfccs, chroma, mel, contrast,tonnetz = extract_feature(fn)
            ext_features = np.hstack([mfccs,chroma,mel,contrast,tonnetz])
            features = np.vstack([features,ext_features])
            labels = np.append(labels, fn.split('/')[2].split('-')[1])
    return np.array(features), np.array(labels, dtype = np.int)

def one_hot_encode(labels):
    n_labels = len(labels)
    n_unique_labels = len(np.unique(labels))
    one_hot_encode = np.zeros((n_labels,n_unique_labels))
    one_hot_encode[np.arange(n_labels), labels] = 1
    return one_hot_encode


def printStuff(msg, arg):
    """ Print msg+perc to stdout and flush 
    msg = "Converting control data %d%%"
    """
    sys.stdout.write('\r')
    sys.stdout.write(msg % (arg))
    sys.stdout.flush()