def __init__(self):
self.nc1 = nc.noteClass()
self.ptSeg1 = ptSeg.pitchtrackSegByNotes()
self.evalu1 = evalu.Evaluation()
self.evaluationMetrics = []
self.resetRepresentation()
def __init__(self):
self.nc1 = nc.noteClass()
self.ptSeg1 = ptSeg.pitchtrackSegByNotes()
self.evalu1 = evalu.Evaluation()
self.evaluationMetrics = []
self.resetRepresentation()
def noteSegmentationFeatureExtraction(self,pitchtrackNoteFolderPath,featureVecFolderPath,pitchtrackNotePredictFolderPath,
recordingNames,segCoef=0.2,predict=False,evaluation=False):
'''
This process will do 1) segment pitchtrack into notes which boundaries are given by pYIN
2) refined segmentation searching stable part
3) calculate features on refined segments
:param pitchtrackNoteFolderPath:
:param featureVecFolderPath:
:param recordingNames:
:param predict:
:return: refined segments boundaries, refined segments pitch contours
'''
############################################## segmentation ########################################################
# below two lines will do segmentaion on calculation the pyin
# ptSeg = pitchtrackSegByNotes.pitchtrackSegByNotes(samplingFreq, frameSize, hopSize)
# ptSeg.doSegmentation(pitchtrack, fs.m_oMonoNoteOut)
ptSeg = pitchtrackSegByNotes.pitchtrackSegByNotes()
if evaluation:
evalu1 = evalu.Evaluation() # evaluation object
COnOffall, COnall, OBOnall, OBOffall,gt,st = 0,0,0,0,0,0
for rn in recordingNames:
pitchtrack_filename = pitchtrackNoteFolderPath+rn+'_pitchtrack.csv'
monoNoteOut_filename = pitchtrackNoteFolderPath+rn+'_monoNoteOut.csv'
ptSeg.doSegmentationForPyinVamp(pitchtrack_filename, monoNoteOut_filename)
if evaluation:
coarseSegmentation_filename = pitchtrackNoteFolderPath+rn+'_coarseSeg.txt'
ptSeg.coarseSegmentation(monoNoteOut_filename,coarseSegmentation_filename) # groundtruth segmentation
# ptSeg.pltNotePitchtrack(saveFig=True, figFolder='../jingjuSegPic/laosheng/train/male_13/pos_3_midinote/')
###################### calculate the polynomial fitting coefs and vibrato frequency ############################
# use pitch track ptseg.pitchtrackByNotes from last step
featureDict = {} # feature vectors dictionary
segmentsExport = {} # refined segmentation boundaries
refinedPitchcontours = {} # refined pitch contours
extremas = {} # extremas
vibrato = {}
curvefittingDeg = 1
jj = 1
jjNone = []
jjj = 1
for ii in range(len(ptSeg.pitchtrackByNotes)):
pt = ptSeg.pitchtrackByNotes[ii][0]
pt = np.array(pt, dtype=np.float32)
x, y = self.normalizeNotePt(pt) # normalise x to [0,1], remove y DC
sbp = self.localMinMax(y) # local minima and extrema of pitch track
self.diffExtrema(x,y) # the amplitude difference of minima and extrema
self.segmentPointDetection1(segCoef) # do the extrema segmentation here
# nc1.segmentPointDetection2() # segmentation point
self.segmentRefinement(pt) # do the refined segmentation
#print self.refinedNotePts
for rpt in self.refinedNotePts:
# print jj
featureVec,extrema,vibOut = self.featureExtractionProcess(rpt,sbp,curvefittingDeg)
if featureVec[0]:
refinedPitchcontours[jj] = rpt.tolist()
featureDict[jj] = featureVec.tolist()
extremas[jj] = extrema
vibrato[jj] = vibOut
else:
jjNone.append(jj)
# this plot step is slow, if we only want the features, we can comment this line
#nc1.pltRefinedNotePtFc(xRpt, yRpt, p, rsquare, polyVar, vibFreq, saveFig=True,
# figFolder='../jingjuSegPic/laosheng/train/refinedSegmentCurvefit/'+rn+'_curvefit_refined/',
# figNumber = jj)
jj += 1
if predict:
# construct the segments frame vector: frame boundary of segments
noteStartFrame = ptSeg.noteStartEndFrame[ii][0]
noteEndFrame = ptSeg.noteStartEndFrame[ii][1]
extremaInd = np.array(self.extrema)
segmentsInd = extremaInd[self.segments]+noteStartFrame
segmentsInd = np.insert(segmentsInd,0,noteStartFrame)
segmentsInd = np.append(segmentsInd,noteEndFrame)+2 # +2 for sonicVisualizer alignment
# segmentsExport[jjj] = str(segmentsInd)
for kk in range(len(segmentsInd)-1):
if jjj not in jjNone:
segmentsExport[jjj] = [segmentsInd[kk],segmentsInd[kk+1]] # segmentation boundary
jjj += 1
if evaluation:
# evaluate segmentation
COnOff, COn, OBOn, OBOff = \
evalu1.coarseEval(ptSeg.coarseSegmentationStartEndFrame,segmentsExport.values())
COnOffall += COnOff
COnall += COn
OBOnall += OBOn
OBOffall += OBOff
gt += len(ptSeg.coarseSegmentationStartEndFrame)
st += len(segmentsExport.values())
# write feature into json
featureFilename = featureVecFolderPath+rn+'.json'
with open(featureFilename, 'w') as outfile:
json.dump(featureDict, outfile)
if predict:
# output segments boundary frames pitch contours
outJsonDict = {'refinedPitchcontours':refinedPitchcontours,'boundary':segmentsExport,
'extremas':extremas,'vibrato':vibrato}
with open(pitchtrackNotePredictFolderPath+rn+'_refinedSegmentFeatures.json', "w") as outfile:
json.dump(outJsonDict,outfile)
# for se in segmentsExport:
# # outfile.write(str(int(se[0]))+'\t'+str(se[1])+'\n')
# outfile.write(str(se)+'\n')
if evaluation:
# print COnOffall,COnall,OBOnall,OBOffall,gt,st
COnOffF,COnF,OBOnRateGT,OBOffRateGT = evalu1.metrics(COnOffall,COnall,OBOnall,OBOffall,gt,st)
return COnOffF,COnF,OBOnRateGT,OBOffRateGT
def noteSegmentationFeatureExtraction(self,
pitchtrackNoteFolderPath,
featureVecFolderPath,
pitchtrackNotePredictFolderPath,
recordingNames,
segCoef=0.2,
predict=False,
evaluation=False):
'''
This process will do 1) segment pitchtrack into notes which boundaries are given by pYIN
2) refined segmentation searching stable part
3) calculate features on refined segments
:param pitchtrackNoteFolderPath:
:param featureVecFolderPath:
:param recordingNames:
:param predict:
:return: refined segments boundaries, refined segments pitch contours
'''
############################################## segmentation ########################################################
# below two lines will do segmentaion on calculation the pyin
# ptSeg = pitchtrackSegByNotes.pitchtrackSegByNotes(samplingFreq, frameSize, hopSize)
# ptSeg.doSegmentation(pitchtrack, fs.m_oMonoNoteOut)
ptSeg = pitchtrackSegByNotes.pitchtrackSegByNotes()
if evaluation:
evalu1 = evalu.Evaluation() # evaluation object
COnOffall, COnall, OBOnall, OBOffall, gt, st = 0, 0, 0, 0, 0, 0
for rn in recordingNames:
pitchtrack_filename = os.path.join(pitchtrackNoteFolderPath,
rn + '_pitchtrack.csv')
monoNoteOut_filename = os.path.join(pitchtrackNoteFolderPath,
rn + '_monoNoteOut.csv')
ptSeg.doSegmentationForPyinVamp(pitchtrack_filename,
monoNoteOut_filename)
if evaluation:
coarseSegmentation_filename = os.path.join(
pitchtrackNoteFolderPath, rn + '_coarseSeg.txt')
ptSeg.coarseSegmentation(
monoNoteOut_filename,
coarseSegmentation_filename) # groundtruth segmentation
# ptSeg.pltNotePitchtrack(saveFig=True, figFolder='../jingjuSegPic/laosheng/train/male_13/pos_3_midinote/')
###################### calculate the polynomial fitting coefs and vibrato frequency ############################
# use pitch track ptseg.pitchtrackByNotes from last step
featureDict = {} # feature vectors dictionary
segmentsExport = {} # refined segmentation boundaries
refinedPitchcontours = {} # refined pitch contours
extremas = {} # extremas
vibrato = {}
curvefittingDeg = 1
jj = 1
jjNone = []
jjj = 1
for ii in range(len(ptSeg.pitchtrackByNotes)):
pt = ptSeg.pitchtrackByNotes[ii][0]
pt = np.array(pt, dtype=np.float32)
x, y = self.normalizeNotePt(
pt) # normalise x to [0,1], remove y DC
sbp = self.localMinMax(
y) # local minima and extrema of pitch track
self.diffExtrema(
x, y) # the amplitude difference of minima and extrema
self.segmentPointDetection1(
segCoef) # do the extrema segmentation here
# nc1.segmentPointDetection2() # segmentation point
self.segmentRefinement(pt) # do the refined segmentation
#print self.refinedNotePts
for rpt in self.refinedNotePts:
# print jj
featureVec, extrema, vibOut = self.featureExtractionProcess(
rpt, sbp, curvefittingDeg)
if featureVec[0]:
refinedPitchcontours[jj] = rpt.tolist()
featureDict[jj] = featureVec.tolist()
extremas[jj] = extrema
vibrato[jj] = vibOut
else:
jjNone.append(jj)
# this plot step is slow, if we only want the features, we can comment this line
#nc1.pltRefinedNotePtFc(xRpt, yRpt, p, rsquare, polyVar, vibFreq, saveFig=True,
# figFolder='../jingjuSegPic/laosheng/train/refinedSegmentCurvefit/'+rn+'_curvefit_refined/',
# figNumber = jj)
jj += 1
if predict:
# construct the segments frame vector: frame boundary of segments
noteStartFrame = ptSeg.noteStartEndFrame[ii][0]
noteEndFrame = ptSeg.noteStartEndFrame[ii][1]
extremaInd = np.array(self.extrema)
segmentsInd = extremaInd[self.segments] + noteStartFrame
segmentsInd = np.insert(segmentsInd, 0, noteStartFrame)
segmentsInd = np.append(
segmentsInd,
noteEndFrame) + 2 # +2 for sonicVisualizer alignment
# segmentsExport[jjj] = str(segmentsInd)
for kk in range(len(segmentsInd) - 1):
if jjj not in jjNone:
segmentsExport[jjj] = [
segmentsInd[kk], segmentsInd[kk + 1]
] # segmentation boundary
jjj += 1
if evaluation:
# evaluate segmentation
COnOff, COn, OBOn, OBOff = \
evalu1.coarseEval(ptSeg.coarseSegmentationStartEndFrame,segmentsExport.values())
COnOffall += COnOff
COnall += COn
OBOnall += OBOn
OBOffall += OBOff
gt += len(ptSeg.coarseSegmentationStartEndFrame)
st += len(segmentsExport.values())
# write feature into json
featureFilename = os.path.join(featureVecFolderPath,
'%s.json' % rn)
with open(featureFilename, 'w') as outfile:
json.dump(featureDict, outfile)
if predict:
# output segments boundary frames pitch contours
outJsonDict = {
'refinedPitchcontours': refinedPitchcontours,
'boundary': segmentsExport,
'extremas': extremas,
'vibrato': vibrato
}
refined_segment_filename = os.path.join(
pitchtrackNotePredictFolderPath,
'%s_refinedSegmentFeatures.json' % rn)
with open(refined_segment_filename, "w") as outfile:
json.dump(outJsonDict, outfile)
# for se in segmentsExport:
# # outfile.write(str(int(se[0]))+'\t'+str(se[1])+'\n')
# outfile.write(str(se)+'\n')
if evaluation:
# print COnOffall,COnall,OBOnall,OBOffall,gt,st
COnOffF, COnF, OBOnRateGT, OBOffRateGT = evalu1.metrics(
COnOffall, COnall, OBOnall, OBOffall, gt, st)
return COnOffF, COnF, OBOnRateGT, OBOffRateGT
