def mtFileClassification(inputFile, modelName, modelType, plotResults=False, gtFile=""):
'''
This function performs mid-term classification of an audio stream.
Towards this end, supervised knowledge is used, i.e. a pre-trained classifier.
ARGUMENTS:
- inputFile: path of the input WAV file
- modelName: name of the classification model
- modelType: svm or knn depending on the classifier type
- plotResults: True if results are to be plotted using matplotlib along with a set of statistics
RETURNS:
- segs: a sequence of segment's endpoints: segs[i] is the endpoint of the i-th segment (in seconds)
- classes: a sequence of class flags: class[i] is the class ID of the i-th segment
'''
if not os.path.isfile(modelName):
print "mtFileClassificationError: input modelType not found!"
return (-1, -1, -1)
# Load classifier:
if modelType == 'svm':
[Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep, computeBEAT] = aT.loadSVModel(modelName)
elif modelType == 'knn':
[Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep, computeBEAT] = aT.loadKNNModel(modelName)
elif modelType == 'randomforest':
[Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep, computeBEAT] = aT.loadRandomForestModel(modelName)
elif modelType == 'gradientboosting':
[Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep, computeBEAT] = aT.loadGradientBoostingModel(modelName)
elif modelType == 'extratrees':
[Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep, computeBEAT] = aT.loadExtraTreesModel(modelName)
if computeBEAT:
print "Model " + modelName + " contains long-term music features (beat etc) and cannot be used in segmentation"
return (-1, -1, -1)
[Fs, x] = audioBasicIO.readAudioFile(inputFile) # load input file
if Fs == -1: # could not read file
return (-1, -1, -1)
x = audioBasicIO.stereo2mono(x) # convert stereo (if) to mono
Duration = len(x) / Fs
# mid-term feature extraction:
[MidTermFeatures, _] = aF.mtFeatureExtraction(x, Fs, mtWin * Fs, mtStep * Fs, round(Fs * stWin), round(Fs * stStep))
flags = []
Ps = []
flagsInd = []
for i in range(MidTermFeatures.shape[1]): # for each feature vector (i.e. for each fix-sized segment):
curFV = (MidTermFeatures[:, i] - MEAN) / STD # normalize current feature vector
[Result, P] = aT.classifierWrapper(Classifier, modelType, curFV) # classify vector
flagsInd.append(Result)
flags.append(classNames[int(Result)]) # update class label matrix
Ps.append(numpy.max(P)) # update probability matrix
flagsInd = numpy.array(flagsInd)
# 1-window smoothing
for i in range(1, len(flagsInd) - 1):
if flagsInd[i-1] == flagsInd[i + 1]:
flagsInd[i] = flagsInd[i + 1]
(segs, classes) = flags2segs(flags, mtStep) # convert fix-sized flags to segments and classes
segs[-1] = len(x) / float(Fs)
# Load grount-truth:
if os.path.isfile(gtFile):
[segStartGT, segEndGT, segLabelsGT] = readSegmentGT(gtFile)
flagsGT, classNamesGT = segs2flags(segStartGT, segEndGT, segLabelsGT, mtStep)
flagsIndGT = []
for j, fl in enumerate(flagsGT): # "align" labels with GT
if classNamesGT[flagsGT[j]] in classNames:
flagsIndGT.append(classNames.index(classNamesGT[flagsGT[j]]))
else:
flagsIndGT.append(-1)
flagsIndGT = numpy.array(flagsIndGT)
CM = numpy.zeros((len(classNamesGT), len(classNamesGT)))
for i in range(min(flagsInd.shape[0], flagsIndGT.shape[0])):
CM[int(flagsIndGT[i]),int(flagsInd[i])] += 1
else:
CM = []
flagsIndGT = numpy.array([])
acc = plotSegmentationResults(flagsInd, flagsIndGT, classNames, mtStep, not plotResults)
if acc >= 0:
print "Overall Accuracy: {0:.3f}".format(acc)
return (flagsInd, classNamesGT, acc, CM)
else:
return (flagsInd, classNames, acc, CM)
def mtFileClassification(inputFile,
modelName,
modelType,
plotResults=False,
gtFile=""):
'''
This function performs mid-term classification of an audio stream.
Towards this end, supervised knowledge is used, i.e. a pre-trained classifier.
ARGUMENTS:
- inputFile: path of the input WAV file
- modelName: name of the classification model
- modelType: svm or knn depending on the classifier type
- plotResults: True if results are to be plotted using matplotlib along with a set of statistics
RETURNS:
- segs: a sequence of segment's endpoints: segs[i] is the endpoint of the i-th segment (in seconds)
- classes: a sequence of class flags: class[i] is the class ID of the i-th segment
'''
if not os.path.isfile(modelName):
print "mtFileClassificationError: input modelType not found!"
return (-1, -1, -1)
# Load classifier:
if modelType == 'svm':
[
Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep,
computeBEAT
] = aT.loadSVModel(modelName)
elif modelType == 'knn':
[
Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep,
computeBEAT
] = aT.loadKNNModel(modelName)
elif modelType == 'randomforest':
[
Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep,
computeBEAT
] = aT.loadRandomForestModel(modelName)
elif modelType == 'gradientboosting':
[
Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep,
computeBEAT
] = aT.loadGradientBoostingModel(modelName)
elif modelType == 'extratrees':
[
Classifier, MEAN, STD, classNames, mtWin, mtStep, stWin, stStep,
computeBEAT
] = aT.loadExtraTreesModel(modelName)
if computeBEAT:
print "Model " + modelName + " contains long-term music features (beat etc) and cannot be used in segmentation"
return (-1, -1, -1)
[Fs, x] = audioBasicIO.readAudioFile(inputFile) # load input file
if Fs == -1: # could not read file
return (-1, -1, -1)
x = audioBasicIO.stereo2mono(x) # convert stereo (if) to mono
Duration = len(x) / Fs
# mid-term feature extraction:
[MidTermFeatures, _] = aF.mtFeatureExtraction(x, Fs,
mtWin * Fs, mtStep * Fs,
round(Fs * stWin),
round(Fs * stStep))
flags = []
Ps = []
flagsInd = []
for i in range(
MidTermFeatures.shape[1]
): # for each feature vector (i.e. for each fix-sized segment):
curFV = (MidTermFeatures[:, i] -
MEAN) / STD # normalize current feature vector
[Result, P] = aT.classifierWrapper(Classifier, modelType,
curFV) # classify vector
flagsInd.append(Result)
flags.append(classNames[int(Result)]) # update class label matrix
Ps.append(numpy.max(P)) # update probability matrix
flagsInd = numpy.array(flagsInd)
# 1-window smoothing
for i in range(1, len(flagsInd) - 1):
if flagsInd[i - 1] == flagsInd[i + 1]:
flagsInd[i] = flagsInd[i + 1]
(segs, classes) = flags2segs(
flags, mtStep) # convert fix-sized flags to segments and classes
segs[-1] = len(x) / float(Fs)
# Load grount-truth:
if os.path.isfile(gtFile):
[segStartGT, segEndGT, segLabelsGT] = readSegmentGT(gtFile)
flagsGT, classNamesGT = segs2flags(segStartGT, segEndGT, segLabelsGT,
mtStep)
flagsIndGT = []
for j, fl in enumerate(flagsGT): # "align" labels with GT
if classNamesGT[flagsGT[j]] in classNames:
flagsIndGT.append(classNames.index(classNamesGT[flagsGT[j]]))
else:
flagsIndGT.append(-1)
flagsIndGT = numpy.array(flagsIndGT)
CM = numpy.zeros((len(classNamesGT), len(classNamesGT)))
for i in range(min(flagsInd.shape[0], flagsIndGT.shape[0])):
CM[int(flagsIndGT[i]), int(flagsInd[i])] += 1
else:
CM = []
flagsIndGT = numpy.array([])
acc = plotSegmentationResults(flagsInd, flagsIndGT, classNames, mtStep,
not plotResults)
if acc >= 0:
print "Overall Accuracy: {0:.3f}".format(acc)
return (flagsInd, classNamesGT, acc, CM)
else:
return (flagsInd, classNames, acc, CM)