def analHpsModelStreaming(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']) # pitch detection pitchDetect = es.PitchYinFFT(frameSize=params['frameSize'], sampleRate=params['sampleRate']) smanal = es.HpsModelAnal(sampleRate=params['sampleRate'], hopSize=params['hopSize'], maxnSines=params['maxnSines'], magnitudeThreshold=params['magnitudeThreshold'], freqDevOffset=params['freqDevOffset'], freqDevSlope=params['freqDevSlope'], minFrequency=params['minFrequency'], maxFrequency=params['maxFrequency'], stocf=params['stocf']) # 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 spec.spectrum >> pitchDetect.spectrum fcut.frame >> smanal.frame pitchDetect.pitch >> smanal.pitch pitchDetect.pitch >> (pool, 'pitch') pitchDetect.pitchConfidence >> (pool, 'pitchConfidence') smanal.magnitudes >> (pool, 'magnitudes') smanal.frequencies >> (pool, 'frequencies') smanal.phases >> (pool, 'phases') smanal.stocenv >> (pool, 'stocenv') essentia.run(insignal) # remove first half window frames mags = pool['magnitudes'] freqs = pool['frequencies'] phases = pool['phases'] pitchConf = pool['pitchConfidence'] # remove short tracks minFrames = int(params['minSineDur'] * params['sampleRate'] / params['hopSize']) freqsClean = cleaningHarmonicTracks(freqs, minFrames, pitchConf) pool['frequencies'].data = freqsClean return mags, freqsClean, phases
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 analsynthHprModelStreaming(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']); # pitch detection pitchDetect = es.PitchYinFFT(frameSize=params['frameSize'], sampleRate = params['sampleRate']) smanal = es.HprModelAnal(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 >> w.frame w.frame >> spec.frame spec.spectrum >> pitchDetect.spectrum fcut.frame >> smanal.frame pitchDetect.pitch >> smanal.pitch pitchDetect.pitchConfidence >> (pool, 'pitchConfidence') pitchDetect.pitch >> (pool, 'pitch') # 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 analsynthHarmonicModelStreaming(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']) smanal = es.HarmonicModelAnal( sampleRate=params['sampleRate'], maxnSines=params['maxnSines'], magnitudeThreshold=params['magnitudeThreshold'], freqDevOffset=params['freqDevOffset'], freqDevSlope=params['freqDevSlope'], minFrequency=params['minFrequency'], maxFrequency=params['maxFrequency']) 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']) # 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 >> smanal.fft pitchDetect.pitch >> smanal.pitch pitchDetect.pitchConfidence >> (pool, 'pitchConfidence') 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