def analysisSynthesisStreaming(params, signal):
out = numpy.array(0)
pool = essentia.Pool()
fcut = es.FrameCutter(frameSize=params['frameSize'],
hopSize=params['hopSize'],
startFromZero=False)
w = es.Windowing(type="hann")
fft = es.FFT(size=params['frameSize'])
ifft = es.IFFT(size=params['frameSize'])
overl = es.OverlapAdd(frameSize=params['frameSize'],
hopSize=params['hopSize'])
# add half window of zeros to input signal to reach same ooutput length
signal = numpy.append(signal, zeros(params['frameSize'] / 2))
insignal = VectorInput(signal)
insignal.data >> fcut.signal
fcut.frame >> w.frame
w.frame >> fft.frame
fft.fft >> ifft.fft
ifft.frame >> overl.frame
overl.signal >> (pool, 'audio')
essentia.run(insignal)
# remove first half window frames
outaudio = pool['audio']
outaudio = outaudio[2 * params['hopSize']:]
return outaudio
def analHarmonicModelStreaming(params, signal):
#out = numpy.array(0)
pool = essentia.Pool()
# windowing and FFT
fcut = es.FrameCutter(frameSize=params['frameSize'],
hopSize=params['hopSize'],
startFromZero=False)
w = es.Windowing(type="blackmanharris92")
fft = es.FFT(size=params['frameSize'])
spec = es.Spectrum(size=params['frameSize'])
# pitch detection
pitchDetect = es.PitchYinFFT(frameSize=params['frameSize'],
sampleRate=params['sampleRate'])
smanal = es.HarmonicModelAnal(
sampleRate=params['sampleRate'],
maxnSines=params['maxnSines'],
magnitudeThreshold=params['magnitudeThreshold'],
freqDevOffset=params['freqDevOffset'],
freqDevSlope=params['freqDevSlope'])
# add half window of zeros to input signal to reach same ooutput length
signal = numpy.append(signal, zeros(params['frameSize'] / 2))
insignal = VectorInput(signal)
insignal.data >> fcut.signal
fcut.frame >> w.frame
w.frame >> spec.frame
w.frame >> fft.frame
spec.spectrum >> pitchDetect.spectrum
fft.fft >> smanal.fft
pitchDetect.pitch >> smanal.pitch
pitchDetect.pitchConfidence >> (pool, 'pitchConfidence')
smanal.magnitudes >> (pool, 'magnitudes')
smanal.frequencies >> (pool, 'frequencies')
smanal.phases >> (pool, 'phases')
essentia.run(insignal)
# remove first half window frames
mags = pool['magnitudes']
freqs = pool['frequencies']
phases = pool['phases']
# remove short tracks
minFrames = int(params['minSineDur'] * params['sampleRate'] /
params['hopSize'])
freqsClean = cleaningSineTracks(freqs, minFrames)
pool['frequencies'].data = freqsClean
return mags, freqsClean, phases
def analsynthSineModelStreaming(params, signal):
out = numpy.array(0)
pool = essentia.Pool()
fcut = es.FrameCutter(frameSize=params['frameSize'],
hopSize=params['hopSize'],
startFromZero=False)
w = es.Windowing(type="blackmanharris92")
fft = es.FFT(size=params['frameSize'])
smanal = es.SineModelAnal(sampleRate=params['sampleRate'],
maxnSines=params['maxnSines'],
magnitudeThreshold=params['magnitudeThreshold'],
freqDevOffset=params['freqDevOffset'],
freqDevSlope=params['freqDevSlope'])
smsyn = es.SineModelSynth(sampleRate=params['sampleRate'],
fftSize=params['frameSize'],
hopSize=params['hopSize'])
ifft = es.IFFT(size=params['frameSize'])
overl = es.OverlapAdd(frameSize=params['frameSize'],
hopSize=params['hopSize'],
gain=1. / params['frameSize'])
# add half window of zeros to input signal to reach same ooutput length
signal = numpy.append(signal, zeros(params['frameSize'] / 2))
insignal = VectorInput(signal)
# analysis
insignal.data >> fcut.signal
fcut.frame >> w.frame
w.frame >> fft.frame
fft.fft >> smanal.fft
smanal.magnitudes >> (pool, 'magnitudes')
smanal.frequencies >> (pool, 'frequencies')
smanal.phases >> (pool, 'phases')
# synthesis
smanal.magnitudes >> smsyn.magnitudes
smanal.frequencies >> smsyn.frequencies
smanal.phases >> smsyn.phases
smsyn.fft >> ifft.fft
ifft.frame >> overl.frame
overl.signal >> (pool, 'audio')
essentia.run(insignal)
# remove short tracks
freqs = pool['frequencies']
minFrames = int(params['minSineDur'] * params['sampleRate'] /
params['hopSize'])
freqsClean = cleaningSineTracks(freqs, minFrames)
pool['frequencies'].data = freqsClean
# remove first half window frames
outaudio = pool['audio']
outaudio = outaudio[2 * params['hopSize']:]
return outaudio, pool
def analsynthHarmonicMaskStreaming(params, signal):
out = array([0.])
pool = essentia.Pool()
# windowing and FFT
fcut = es.FrameCutter(frameSize=params['frameSize'],
hopSize=params['hopSize'],
startFromZero=False)
w = es.Windowing(type="blackmanharris92")
fft = es.FFT(size=params['frameSize'])
spec = es.Spectrum(size=params['frameSize'])
# pitch detection
pitchDetect = es.PitchYinFFT(frameSize=params['frameSize'],
sampleRate=params['sampleRate'])
hmask = es.HarmonicMask(sampleRate=params['sampleRate'],
binWidth=params['binWidth'],
attenuation=params['attenuation_dB'])
ifft = es.IFFT(size=params['frameSize'])
overl = es.OverlapAdd(frameSize=params['frameSize'],
hopSize=params['hopSize'])
# add half window of zeros to input signal to reach same ooutput length
signal = numpy.append(signal, zeros(params['frameSize'] // 2))
insignal = VectorInput(signal)
# analysis
insignal.data >> fcut.signal
fcut.frame >> w.frame
w.frame >> spec.frame
w.frame >> fft.frame
spec.spectrum >> pitchDetect.spectrum
fft.fft >> hmask.fft
pitchDetect.pitch >> hmask.pitch
pitchDetect.pitchConfidence >> (pool, 'pitchConfidence')
hmask.fft >> ifft.fft
ifft.frame >> overl.frame
overl.signal >> (pool, 'audio')
essentia.run(insignal)
# remove first half window frames
outaudio = pool['audio']
outaudio = outaudio[2 * params['hopSize']:]
return outaudio, pool
def analsynthSineSubtractionStreaming(params, signal):
out = numpy.array(0)
pool = essentia.Pool()
fcut = es.FrameCutter(frameSize=params['frameSize'],
hopSize=params['hopSize'],
startFromZero=False)
w = es.Windowing(type="blackmanharris92")
fft = es.FFT(size=params['frameSize'])
smanal = es.SineModelAnal(sampleRate=params['sampleRate'],
maxnSines=params['maxnSines'],
magnitudeThreshold=params['magnitudeThreshold'],
freqDevOffset=params['freqDevOffset'],
freqDevSlope=params['freqDevSlope'])
subtrFFTSize = min(params['frameSize'] / 4, 4 * params['hopSize'])
smsub = es.SineSubtraction(sampleRate=params['sampleRate'],
fftSize=subtrFFTSize,
hopSize=params['hopSize'])
# add half window of zeros to input signal to reach same ooutput length
signal = numpy.append(signal, zeros(params['frameSize'] / 2))
insignal = VectorInput(signal)
# analysis
insignal.data >> fcut.signal
fcut.frame >> w.frame
w.frame >> fft.frame
fft.fft >> smanal.fft
smanal.magnitudes >> (pool, 'magnitudes')
smanal.frequencies >> (pool, 'frequencies')
smanal.phases >> (pool, 'phases')
# subtraction
fcut.frame >> smsub.frame
smanal.magnitudes >> smsub.magnitudes
smanal.frequencies >> smsub.frequencies
smanal.phases >> smsub.phases
smsub.frame >> (pool, 'frames')
essentia.run(insignal)
print pool['frames'].shape
outaudio = framesToAudio(pool['frames'])
outaudio = outaudio[2 * params['hopSize']:]
return outaudio, pool
def analSineModelStreaming(params, signal):
#out = numpy.array(0)
pool = essentia.Pool()
fcut = es.FrameCutter(frameSize=params['frameSize'],
hopSize=params['hopSize'],
startFromZero=False)
w = es.Windowing(type="hann")
fft = es.FFT(size=params['frameSize'])
smanal = es.SineModelAnal(sampleRate=params['sampleRate'],
maxnSines=params['maxnSines'],
magnitudeThreshold=params['magnitudeThreshold'],
freqDevOffset=params['freqDevOffset'],
freqDevSlope=params['freqDevSlope'])
# add half window of zeros to input signal to reach same ooutput length
signal = numpy.append(signal, zeros(params['frameSize'] / 2))
insignal = VectorInput(signal)
insignal.data >> fcut.signal
fcut.frame >> w.frame
w.frame >> fft.frame
fft.fft >> smanal.fft
smanal.magnitudes >> (pool, 'magnitudes')
smanal.frequencies >> (pool, 'frequencies')
smanal.phases >> (pool, 'phases')
essentia.run(insignal)
# remove first half window frames
mags = pool['magnitudes']
freqs = pool['frequencies']
phases = pool['phases']
# remove short tracks
minFrames = int(params['minSineDur'] * params['sampleRate'] /
params['hopSize'])
freqsClean = cleaningSineTracks(freqs, minFrames)
pool['frequencies'].data = freqsClean
return mags, freqsClean, phases
audioout = np.array(0) counter = 0 # input and output files import os.path tutorial_dir = os.path.dirname(os.path.realpath(__file__)) inputFilename = os.path.join(tutorial_dir, 'singing-female.wav') outputFilename = os.path.join(tutorial_dir, 'singing-female-out-sinesubtraction.wav') out = np.array(0) loader = es.MonoLoader(filename = inputFilename, sampleRate = params['sampleRate']) pool = essentia.Pool() fcut = es.FrameCutter(frameSize = params['frameSize'], hopSize = params['hopSize'], startFromZero = False); w = es.Windowing(type = "blackmanharris92"); fft = es.FFT(size = params['frameSize']); smanal = es.SineModelAnal(sampleRate = params['sampleRate'], maxnSines = params['maxnSines'], magnitudeThreshold = params['magnitudeThreshold'], freqDevOffset = params['freqDevOffset'], freqDevSlope = params['freqDevSlope']) subtrFFTSize = min(params['frameSize']/4, 4* params['hopSize']) smsub = es.SineSubtraction(sampleRate = params['sampleRate'], fftSize = subtrFFTSize, hopSize = params['hopSize']) # analysis loader.audio >> fcut.signal fcut.frame >> w.frame w.frame >> fft.frame fft.fft >> smanal.fft smanal.magnitudes >> (pool, 'magnitudes') smanal.frequencies >> (pool, 'frequencies') smanal.phases >> (pool, 'phases') # subtraction fcut.frame >> smsub.frame
if counter >= (framesize/(2*hopsize)):
audioout = np.append(audioout, out)
counter += 1
# write audio output
print audioout.shape
awrite(audioout.astype(np.float32))
if mode == 'streaming':
out = np.array(0)
loader = es.MonoLoader(filename = inputFilename, sampleRate = 44100)
pool = essentia.Pool()
fcut = es.FrameCutter(frameSize = framesize, hopSize = hopsize, startFromZero = False);
w = es.Windowing(type = "hann");
fft = es.FFT(size = framesize);
ifft = es.IFFT(size = framesize);
overl = es.OverlapAdd (frameSize = framesize, hopSize = hopsize);
awrite = es.MonoWriter (filename = outputFilename, sampleRate = 44100);
#gen = audio #VectorInput(audio)
loader.audio >> fcut.signal
fcut.frame >> w.frame
w.frame >> fft.frame
fft.fft >> ifft.fft
ifft.frame >> overl.frame
overl.signal >> awrite.audio
overl.signal >> (pool, 'audio')
essentia.run(loader)
