def analsynthSprModelStreaming(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")
spec = es.Spectrum(size=params['frameSize'])
smanal = es.SprModelAnal(sampleRate=params['sampleRate'],
hopSize=params['hopSize'],
maxnSines=params['maxnSines'],
magnitudeThreshold=params['magnitudeThreshold'],
freqDevOffset=params['freqDevOffset'],
freqDevSlope=params['freqDevSlope'],
minFrequency=params['minFrequency'],
maxFrequency=params['maxFrequency'])
synFFTSize = min(
int(params['frameSize'] / 4),
4 * params['hopSize']) # make sure the FFT size is appropriate
smsyn = es.SprModelSynth(sampleRate=params['sampleRate'],
fftSize=synFFTSize,
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 >> smanal.frame
# synthesis
smanal.magnitudes >> smsyn.magnitudes
smanal.frequencies >> smsyn.frequencies
smanal.phases >> smsyn.phases
smanal.res >> smsyn.res
smsyn.frame >> (pool, 'frames')
smsyn.sineframe >> (pool, 'sineframes')
smsyn.resframe >> (pool, 'resframes')
essentia.run(insignal)
outaudio = framesToAudio(pool['frames'])
outaudio = outaudio[2 * params['hopSize']:]
return outaudio, pool
def analSprModelStreaming(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")
spec = es.Spectrum(size=params['frameSize'])
smanal = es.SprModelAnal(sampleRate=params['sampleRate'],
maxnSines=params['maxnSines'],
magnitudeThreshold=params['magnitudeThreshold'],
freqDevOffset=params['freqDevOffset'],
freqDevSlope=params['freqDevSlope'],
minFrequency=params['minFrequency'],
maxFrequency=params['maxFrequency'])
# 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 >> smanal.frame
smanal.magnitudes >> (pool, 'magnitudes')
smanal.frequencies >> (pool, 'frequencies')
smanal.phases >> (pool, 'phases')
smanal.res >> (pool, 'res')
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
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-sprmodel.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.SprModelAnal(sampleRate=params['sampleRate'],
maxnSines=params['maxnSines'],
magnitudeThreshold=params['magnitudeThreshold'],
freqDevOffset=params['freqDevOffset'],
freqDevSlope=params['freqDevSlope'])
synFFTSize = min(int(params['frameSize'] / 4), 4 * params['hopSize'])
# make sure the FFT size is appropriate
smsyn = es.SprModelSynth(sampleRate=params['sampleRate'],
fftSize=synFFTSize,
hopSize=params['hopSize'])
# analysis
loader.audio >> fcut.signal
fcut.frame >> smanal.frame
smanal.magnitudes >> (pool, 'magnitudes')
smanal.frequencies >> (pool, 'frequencies')
smanal.phases >> (pool, 'phases')