def training(nfiltbank, orderLPC):
#Get directory and list of *.wav files
directory = os.getcwd() + '/train_all_speakers'
wave_files = [f for f in os.listdir(directory)]
nSpeaker = len(wave_files)
nCentroid = 32 # original is 16
codebooks_mfcc = np.empty((nSpeaker, nfiltbank, nCentroid))
codebooks_lpc = np.empty((nSpeaker, orderLPC, nCentroid))
for i, wave_file in enumerate(wave_files):
fname = '/' + wave_file
print 'Speaker [' + str(
i) + '] File:' + wave_file + ' Training features...'
(fs, s) = read(directory + fname)
mel_coeff = mfcc_p(s, fs)
mel_coeff = mel_coeff.transpose()
mel_coeff[0, :] = np.zeros(mel_coeff.shape[1])
lpc_coeff = lpc(s, fs, orderLPC)
codebooks_mfcc[i, :, :] = lbg(mel_coeff, nCentroid)
codebooks_lpc[i, :, :] = lbg(lpc_coeff, nCentroid)
print('Training finished\n')
return (codebooks_mfcc, codebooks_lpc)
speaker = k
return speaker
print "|||||STARTING TEST|||||\n"
for i, wave_file in enumerate(wave_files):
fname = '/' + wave_file
to_print = 'Speaker [' + str(
i) + '] File:' + wave_file + ' Testing features...'
print to_print
(fs, s) = read(directory + fname)
#Passing test file to MFCC
mel_coefs = mfcc_p(s, fs)
mel_coefs = mel_coefs.transpose()
mel_coefs[0, :] = np.zeros(
mel_coefs.shape[1]
) # 0th coefficient does not carry significant information
#Passing test file to LPC
lpc_coefs = lpc(s, fs, orderLPC)
sp_mfcc = minDistance(mel_coefs, codebooks_mfcc)
sp_lpc = minDistance(lpc_coefs, codebooks_lpc)
print 'Speaker [' + str(i) + '] matches Speaker [' + str(
sp_mfcc) + '] ||MFCC||'
print 'Speaker [' + str(i) + '] matches Speaker [' + str(
sp_lpc) + '] ||LPC||\n'
def training(nfiltbank, orderLPC):
nSpeaker = 8
nCentroid = 32 #original is 16
codebooks_mfcc = np.empty((nSpeaker, nfiltbank, nCentroid))
codebooks_lpc = np.empty((nSpeaker, orderLPC, nCentroid))
directory = os.getcwd() + '/train'
fname = str()
for i in range(nSpeaker):
fname = '/s' + str(i + 1) + '.wav'
print('Now speaker ', str(i + 1), 'features are being trained')
(fs, s) = read(directory + fname)
#altering sample rate
#fs = 10000 #original was 13000
#mel_coeff = mfcc(s, fs, nfiltbank)
mel_coeff = mfcc_p(s, fs)
mel_coeff = mel_coeff.transpose()
mel_coeff[0, :] = np.zeros(mel_coeff.shape[1])
lpc_coeff = lpc(s, fs, orderLPC)
codebooks_mfcc[i, :, :] = lbg(mel_coeff, nCentroid)
codebooks_lpc[i, :, :] = lbg(lpc_coeff, nCentroid)
plt.figure(i)
plt.title('Codebook for speaker ' + str(i + 1) + ' with ' +
str(nCentroid) + ' centroids')
for j in range(nCentroid):
plt.subplot(211)
plt.stem(codebooks_mfcc[i, :, j])
plt.ylabel('MFCC')
plt.subplot(212)
markerline, stemlines, baseline = plt.stem(codebooks_lpc[i, :, j])
plt.setp(markerline, 'markerfacecolor', 'r')
plt.setp(baseline, 'color', 'k')
plt.ylabel('LPC')
plt.axis(ymin=-1, ymax=1)
plt.xlabel('Number of features')
plt.show()
print('Training complete')
# #plotting 5th and 6th dimension MFCC features on a 2D plane
# #comment lines 54 to 71 if you don't want to see codebook
# codebooks = np.empty((2, nfiltbank, nCentroid))
# mel_coeff = np.empty((2, nfiltbank, 68))
#
# for i in range(2):
# fname = '/s' + str(i+2) + '.wav'
# (fs,s) = read(directory + fname)
# #mel_coeff[i,:,:] = mfcc(s, fs, nfiltbank)[:,0:68]
# saver = mfcc_p(s, fs)
# mel_coeff[i, :, :] = saver.transpose()[:,0:68]
# codebooks[i,:,:] = lbg(mel_coeff[i,:,:], nCentroid)
#
#
# plt.figure(nSpeaker + 1)
# s1 = plt.scatter(mel_coeff[0,6,:], mel_coeff[0,4,:],s = 100, color = 'r', marker = 'o')
# c1 = plt.scatter(codebooks[0,6,:], codebooks[0,4,:], s = 100, color = 'r', marker = '+')
# s2 = plt.scatter(mel_coeff[1,6,:], mel_coeff[1,4,:],s = 100, color = 'b', marker = 'o')
# c2 = plt.scatter(codebooks[1,6,:], codebooks[1,4,:], s = 100, color = 'b', marker = '+')
# plt.grid()
# plt.legend((s1, s2, c1, c2), ('Sp1','Sp2','Sp1 centroids', 'Sp2 centroids'), scatterpoints = 1, loc = 'upper left')
# plt.show()
return (codebooks_mfcc, codebooks_lpc)
