def MCC_calc(dataPath_true, dataPath_pred, NFFT):
STFT_OVERLAP = 0.5
feat_pred, fs = utils.wavToSamples(dataPath_pred)
#print(len(feat_pred))
feat_true, fs = utils.wavToSamples(dataPath_true)
#print(len(feat_true))
lenPred = len(feat_pred)
lenRef = len(feat_true)
if lenRef < lenPred:
feat_true = np.concatenate((feat_true, np.zeros(lenPred - lenRef)))
elif lenPred < lenRef:
feat_pred = np.concatenate((feat_pred, np.zeros(lenRef - lenPred)))
feat_pred, _, _, _ = utils.STFT(feat_pred, fs, NFFT,
int(NFFT * STFT_OVERLAP))
feat_pred = np.float32(feat_pred)
feat_true, _, _, _ = utils.STFT(feat_true, fs, NFFT,
int(NFFT * STFT_OVERLAP))
feat_true = np.float32(feat_true)
#feat_true = np.array(feat_true)
#feat_pred = np.array(feat_pred)
# Calculate the spectral MCC
xx_true = np.subtract(feat_true,
np.mean(feat_true, 1).reshape(feat_true.shape[0], 1))
denom_true = np.sqrt(np.sum(xx_true**2, 1)).reshape(feat_true.shape[0], 1)
xx_true = np.divide(xx_true, denom_true)
xx_pred = np.subtract(feat_pred,
np.mean(feat_pred, 1).reshape(feat_pred.shape[0], 1))
denom_pred = np.sqrt(np.sum(xx_pred**2, 1)).reshape(feat_pred.shape[0], 1)
xx_pred = np.divide(xx_pred, denom_pred)
segMCC = np.sum(np.multiply(xx_true, xx_pred), 1)
segMCC = segMCC.reshape(feat_pred.shape[0], 1)
MCC = np.mean(segMCC)
freq = np.linspace(0, fs / 2, np.size(segMCC, 0))
# plt.plot(freq,segMCC, linewidth=2)
# plt.xlabel("Frequency [Hz]")
# plt.ylabel("Magnitude Correlation")
# plt.title("MCC")
# plt.grid(linestyle='--')
return MCC, segMCC, freq
def featureExtraction(filePathFeat, AUDIO_dB_SPL, NFFT, STFT_OVERLAP, numBin,
featMean, featStd):
# Feature Extraction function
# filePathFeat : filepath name [string]
# AUDIO_dB_SPL : dB SPL value to adjust SNR level
# NFFT : Number of frequency bins
# STFT_OVERLAP : frame overlab [0 - 1]
# numBin : number of frequency bins you want to use. [0 Hz - ..]
# featMean : features mean value for standardization
# featStd : features standard deviation value for standardization
x, fs = utils.wavToSamples(filePathFeat)
x = utils.adjustSNR(x, AUDIO_dB_SPL)
features, feature_phi, _, _ = utils.STFT(x, fs, NFFT,
int(NFFT * STFT_OVERLAP))
features = np.float32(features)
features = np.log10(features + 1e-7)
features = features - featMean
features = features / featStd
features = np.transpose(features)
features = features[:, 0:numBin]
return features, feature_phi
def calcMeanAndStd(dataPath,NUM_FILES,NFFT,STFT_OVERLAP,BIN_WIZE): allFiles = os.listdir(dataPath) allFiles = allFiles[:NUM_FILES] #averageOld = 0 #stdOld = 0 count = 0 featMean = 0 featStd = 0 for file in allFiles: count += 1 filePath = dataPath + file x, fs = utils.wavToSamples(filePath) x = utils.adjustSNR(x,60) features,feature_phi,_,_ = utils.STFT(x,fs,NFFT,int(NFFT*STFT_OVERLAP)) features = np.float32(features) features = np.log10(features + 1e-7) if BIN_WIZE: featMean = np.asarray(np.mean(features,1)) featStd = np.asarray(np.std(features,1)) else: featMean = featMean + np.mean(features) featStd = featStd + np.std(features) #print((featMean + averageOld)/count) #averageOld = averageOld + (featMean + averageOld)/count #print(averageOld) #stdOld = stdOld + (featStd + stdOld)/count featMean = featMean/count featStd = featStd/count #averageNew = averageOld #stdNew = stdOld return featMean, featStd
x = x[0:int(fs * 6)] #x = signal.decimate(x,3) #fs = 16000 #x = x/np.max(np.abs(x)) fs2, x_ref = wavfile.read(filePath2) #x_ref, fs2 = utils.wavToSamples(filePath2) x_ref = x_ref[0:int(fs2 * 6)] #x_ref = signal.decimate(x_ref,3) #fs2 = 16000 #x_ref = x_ref/np.max(np.abs(x_ref)) wL = 512 features, X_phi, t, f = utils.STFT(x, fs, wL, int(wL * 0.75)) features.shape X_phi.shape labels, L_phi, t2, f2 = utils.STFT(x_ref, fs2, wL, int(wL * 0.75)) labels.shape #### MODEL #### features = np.float32(features) labels = np.float32(labels) #cond1 = np.std(features,axis=1) > 0 #features = features[cond1,:] #cond2 = features == 0 #features[cond2] += np.finfo(float).eps