def song(self,path):
y, sr = librosa.load(self.path, duration=120)
S_full, phase = librosa.magphase(librosa.stft(y))
S_filter = librosa.decompose.nn_filter(S_full,aggregate=np.median,metric='cosine',
width=int(librosa.time_to_frames(2, sr=sr)))
S_filter = np.minimum(S_full, S_filter)
margin_i, margin_v = 2, 10
power = 2
mask_i = librosa.util.softmask(S_filter,margin_i * (S_full - S_filter),power=power)
mask_v = librosa.util.softmask(S_full - S_filter,margin_v * S_filter,power=power)
S_foreground = mask_v * S_full
S_background = mask_i * S_full
music =librosa.griffinlim(S_background)
vocal =librosa.griffinlim(S_foreground)
scipy.io.wavfile.write('sound_results/song/music.wav',sr,music)
scipy.io.wavfile.write('sound_results/song/vocal.wav',sr,vocal)
utl.plotSounds([music, vocal], ["music", "vocal"], sr, "plot_results/song/song_separation_plot.png")
img = pg.QtGui.QGraphicsPixmapItem(pg.QtGui.QPixmap('plot_results/song/song_separation_plot.png'))
self.ui1.widget_song.addItem(img)
self.ui1.widget_song.invertY(True)
self.alarm("Check Plot & Sound Results Files")
def cocktail(self):
eps = 0.00000001
rate1, data1 = wavfile.read(self.path1)
rate2, data2 = wavfile.read(self.path2)
if(data1.ndim != 1 or data2.ndim != 1):
self.alarm("Please Chose another file with 1D data")
else:
data1 = data1 - np.mean(data1)
data1 = data1/max(data1)
data2 = data2 - np.mean(data2)
data2 = data2/max(data2)
signals = [data1, data2]
matrix = np.vstack(signals)
whiteMatrix = utl.whitenMatrix(matrix)
X = whiteMatrix
vectors = []
for i in range(0, X.shape[0]):
vector = FA(X, vectors, eps)
vectors.append(vector)
W = np.vstack(vectors)
S = np.dot(W, whiteMatrix)
utl.plotSounds([S[0], S[1]], ["source_1", "source_2"], rate1, "plot_results/cocktail_party/song_separation_plot.png")
wavfile.write("sound_results/cocktail_party/source1.wav" ,rate1, 5000*S[0].astype(np.int16))
wavfile.write("sound_results/cocktail_party/source2.wav" , rate1, 5000*S[1].astype(np.int16))
img = pg.QtGui.QGraphicsPixmapItem(pg.QtGui.QPixmap('plot_results/cocktail_party/song_separation_plot.png'))
self.ui2.widget_party.addItem(img)
self.ui2.widget_party.invertY(True)
self.alarm("Check Plot & Sound Results Files")
signals = [data1, data2]
matrix = np.vstack(signals)
# Whitening the matrix as a pre-processing step
whiteMatrix = utils.whitenMatrix(matrix)
X = whiteMatrix
# Find the individual components one by one
vectors = []
for i in range(0, X.shape[0]):
# The FastICA function is used as is from FastICA_image.py, and the it works out of the box
vector = FastICA(X, vectors, eps)
vectors.append(vector)
# Stack the vectors to form the unmixing matrix
W = np.vstack(vectors)
# Get the original matrix
S = np.dot(W, whiteMatrix)
# Plot the separated sound signals
utils.plotSounds([S[0], S[1]], ["SignalA", "SignalB"], rate1,
"Ring_StarWars_separated")
# Write the separated sound signals, 5000 is multiplied so that signal is audible
wavfile.write("./ICAseparate" + name[0] + ".wav", rate1,
5000 * S[0].astype(np.int16))
wavfile.write("./ICAseparate" + name[1] + ".wav", rate1,
5000 * S[1].astype(np.int16))
import utilities as utils
from scipy.io import wavfile
import numpy as np
# Read the files as numpy array
rate1, data1 = wavfile.read("sourceA.wav")
rate2, data2 = wavfile.read("sourceB.wav")
# Using the mixSounds helper function from utilities.py
mixedX = utils.mixSounds([data1, data2], [0.3, 0.7]).astype(np.int16)
mixedY = utils.mixSounds([data1, data2], [0.6, 0.4]).astype(np.int16)
# Plot the mixed sound sources
utils.plotSounds([mixedX, mixedY], ["mixedA", "mixedB"], rate1,
"../plots/sounds/Ring_StarWars_mixed", False)
# Save the mixed sources as wav files
wavfile.write("mixedA.wav", rate1, mixedX)
wavfile.write("mixedB.wav", rate1, mixedY)
"""The script makes the sources to have same length,
as well as have the same sampling rate"""
from scipy.io import wavfile
import utilities as utl
# Read the .wav files as numpy arrays
rate1, data1 = wavfile.read("sourceX.wav")
rate2, data2 = wavfile.read("sourceY.wav")
# Plot the sounds as time series data
utl.plotSounds([data1, data2], ["PhoneRing", "StarWars"], rate1,
"../plots/sounds/Ring_StarWars_original")
# Make both of the files to have same length as well as same sampling rate
minimum = min(data1.shape[0], data2.shape[0])
# Slicing the array for both the sources
data1 = data1[0:minimum]
data2 = data2[0:minimum]
# writing the array into to the wav file with sampling rate which is average of the two
wavfile.write("sourceX.wav", (rate1 + rate2) / 2, data1)
wavfile.write("sourceY.wav", (rate1 + rate2) / 2, data2)
vectors.append(vector)
# Stack the vectors to form the unmixing matrix
W = np.vstack(vectors)
# Get the original matrix
S = np.dot(W, whiteMatrix)
# Unmixing matrix through FOBI
fobiW = FOBI(X)
# Get the original matrix using fobiW
fobiS = np.dot(fobiW.T, whiteMatrix)
# Plot the separated sound signals
utl.plotSounds([S[0], S[1]], ["1", "2"], rate1, "Ring_StarWars_separated")
# Write the separated sound signals, 5000 is multiplied so that signal is audible
wavfile.write("./sounds/FOBIseparate" + name[0] + ".wav", rate1,
5000 * S[0].astype(np.int16))
wavfile.write("./sounds/FOBIseparate" + name[1] + ".wav", rate1,
5000 * S[1].astype(np.int16))
# Plot the separated sound signals
utl.plotSounds([fobiS[1], fobiS[0]], ["1", "2"], rate1,
"Ring_StarWars_separated_FOBI")
# Write the separated sound signals, 5000 is multiplied so that signal is audible
wavfile.write("./sounds/FOBIseparate" + name[0] + ".wav", rate1,
5000 * fobiS[1].astype(np.int16))
wavfile.write("./sounds/FOBIseparate" + name[1] + ".wav", rate1,
def separate_sound3(b, name):
name = ["1", "2", "3"]
eps = 0.00000001
#Read the mixed signals
rate1, data1 = wavfile.read(b[0])
rate2, data2 = wavfile.read(b[1])
rate3, data3 = wavfile.read(b[2])
#Centering the mixed signals and scaling the values as well
data1 = data1 - np.mean(data1)
data1 = data1 / 32768
data2 = data2 - np.mean(data2)
data2 = data2 / 32768
data3 = data3 - np.mean(data3)
data3 = data3 / 32768
#Creating a matrix out of the signals
signals = [data1, data2, data3]
matrix = np.vstack(signals)
#Whitening the matrix as a pre-processing step
whiteMatrix = utl.whitenMatrix(matrix)
X = whiteMatrix
#Find the individual components one by one
vectors = []
for i in range(0, X.shape[0]):
#The FastICA function is used as is from FastICA_image.py, and the it works out of the box
vector = FastICA(X, vectors, eps)
vectors.append(vector)
#Stack the vectors to form the unmixing matrix
W = np.vstack(vectors)
#Get the original matrix
S = np.dot(W, whiteMatrix)
#Unmixing matrix through FOBI
fobiW = FOBI(X)
#Get the original matrix using fobiW
fobiS = np.dot(fobiW.T, whiteMatrix)
#Plot the separated sound signals
utl.plotSounds([S[0], S[1], S[2]], ["1", "2", "3"], rate1, "separated")
#Write the separated sound signals, 5000 is multiplied so that signal is audible
wavfile.write(
"C:/SPEECH_SEPARATION--FinalYear/Separated/separate-" + name[0] +
".wav", rate1, 5000 * S[0].astype(np.int16))
wavfile.write(
"C:/SPEECH_SEPARATION--FinalYear/Separated/separate-" + name[1] +
".wav", rate1, 5000 * S[1].astype(np.int16))
wavfile.write(
"C:/SPEECH_SEPARATION--FinalYear/Separated/separate-" + name[2] +
".wav", rate1, 5000 * S[2].astype(np.int16))
#Plot the separated sound signals
utl.plotSounds([fobiS[1], fobiS[0], fobiS[2]], ["1", "2", "3"], rate1,
"separated_FOBI")
#Write the separated sound signals, 5000 is multiplied so that signal is audible
wavfile.write(
"C:/SPEECH_SEPARATION--FinalYear/Separated/separate-" + name[0] +
".wav", rate1, 5000 * fobiS[1].astype(np.int16))
wavfile.write(
"C:/SPEECH_SEPARATION--FinalYear/Separated/separate-" + name[1] +
".wav", rate1, 5000 * fobiS[0].astype(np.int16))
wavfile.write(
"C:/SPEECH_SEPARATION--FinalYear/Separated/separate-" + name[2] +
".wav", rate3, 5000 * fobiS[2].astype(np.int16))
import utilities as utl
from scipy.io import wavfile
import numpy as np
# Read the files as numpy array
rate1, data1 = wavfile.read("13-84-1.wav")
rate2, data2 = wavfile.read("13-172-1.wav")
# Using the mixSounds helper function from utilities.py
mixedX = utl.mixSounds([data1, data2], [0.3, 0.7]).astype(np.int16)
mixedY = utl.mixSounds([data1, data2], [0.6, 0.4]).astype(np.int16)
# Plot the mixed sound sources
utl.plotSounds([mixedX, mixedY], ["mixed-1", "mixed-3"], rate1,
"../plots/sounds/Ring_StarWars_mixed", False)
# Save the mixed sources as wav files
wavfile.write("mixed-1.wav", rate1, mixedX)
wavfile.write("mixed-3.wav", rate1, mixedY)