def get_segments(filepath, seg_length):
afm = af.audiofile_manager(filepath, seg_length)
while afm.HasMoreData():
segment, index = afm.GetNextSegment()
print "%d: %d | (%d of %d)" % (index, segment.shape[0],
index * afm.seg_length_samps,
afm.afReader.numsamples())
def getfeatures(args):
''' write the extracted features from the input audio file into numpy files for reading in the other steps. '''
debug = args.debug
filepath = args.audiofile
chunk_len = args.audio_seg_length
afm = af.audiofile_manager(filepath, chunk_len)
# FFT Parameters
fs = afm.afReader.samplerate()
N = 2048
hopDenom = 2
hopSize = N / hopDenom
zp = 0
winfunc = np.hamming
fftParams = fftparams.FFTParams(fs, N, hopDenom, zp, winfunc)
# MFCC Paramters
nFilters = 40
nDCTCoefs = 20
minFreq = 50
maxFreq = 8000
nIndexSkip = 2
seglen = 1
mfccParams = fftparams.MFCCParams(nFilters, nDCTCoefs, minFreq, maxFreq,
nIndexSkip)
# Feature Vector parameters
# Template : ('name', order index, length)
vector_template = [('sones', 0, 1), ('mfcc', 1, nDCTCoefs - nIndexSkip)]
sone_template = [('sones', 0, 1)]
# Initialize the feature vector holder
feature_holder = featurevector.feature_holder(vector_template, filepath)
sone_holder = featurevector.feature_holder(sone_template, filepath)
envelopeHolder = []
audioHolder = []
sonesHolder = []
maxEnvelope = 0
count = 0
print "Feature Extraction Mode\n"
print datetime.now()
# For each chunk of audio
while afm.HasMoreData():
count += 1
audioChunk, chunkIndex = afm.GetNextSegment()
if debug:
print "Read %d sample chunk of audio (%0.2fs)" % (
len(audioChunk), len(audioChunk) / fs)
# Get Events
eventTimes, envelope = GetEvents(audioChunk, fftParams, debug)
if maxEnvelope < envelope.max():
maxEnvelope = envelope.max()
if debug: print "EVENTTIMES:", eventTimes
envelopeHolder.append(envelope)
eventTimesSamps = np.asarray(np.multiply(eventTimes, fs), dtype=int)
# Get event audio segments
eventSegments = GetEventAudioSegments(eventTimesSamps, audioChunk,
debug)
#get sones
eventSegmentSones = GetEventSones(eventSegments, fftParams, debug)
# Get the MFCCs for each segment / event
eventSegmentMFCCs = GetEventMFCCs(eventSegments, fftParams, mfccParams,
debug)
# Time-average for each segment / event
averagedEventSegmentMFCCs, averagedEventSegmentSones = AverageEventFeatures(
eventSegmentMFCCs, eventSegmentSones, seglen, fftParams, debug)
# Store these vectors in the feature_holder, labelled with their time
StoreFeatureVector(feature_holder, sone_holder,
averagedEventSegmentMFCCs,
averagedEventSegmentSones, chunkIndex, chunk_len,
eventTimes, debug)
# Write features to disk
print datetime.now()
fileSize = feature_holder.save(FEATURE_VECTOR_FILENAME)
print "Wrote", fileSize, "bytes to disk. (%s)" % (FEATURE_VECTOR_FILENAME)
fileSize = sone_holder.save(SONE_VECTOR_FILENAME)
print "Wrote", fileSize, "bytes to disk. (%s)" % (SONE_VECTOR_FILENAME)
def get_segments(filepath, seg_length):
afm = af.audiofile_manager(filepath, seg_length)
while afm.HasMoreData():
segment, index = afm.GetNextSegment()
print "%d: %d | (%d of %d)" % (index, segment.shape[0], index * afm.seg_length_samps, afm.afReader.numsamples())
def getfeatures(args):
''' write the extracted features from the input audio file into numpy files for reading in the other steps. '''
debug = args.debug
filepath = args.audiofile
chunk_len = args.audio_seg_length
afm = af.audiofile_manager(filepath, chunk_len)
# FFT Parameters
fs = afm.afReader.samplerate()
N = 2048
hopDenom = 2
hopSize = N/hopDenom
zp = 0
winfunc=np.hamming
fftParams = fftparams.FFTParams(fs, N, hopDenom, zp, winfunc)
# MFCC Paramters
nFilters = 40
nDCTCoefs = 20
minFreq = 50
maxFreq = 8000
nIndexSkip = 2
seglen = 1
mfccParams = fftparams.MFCCParams(nFilters, nDCTCoefs, minFreq, maxFreq, nIndexSkip)
# Feature Vector parameters
# Template : ('name', order index, length)
vector_template = [('sones', 0, 1),
('mfcc', 1, nDCTCoefs - nIndexSkip)]
sone_template = [('sones', 0, 1)]
# Initialize the feature vector holder
feature_holder = featurevector.feature_holder(vector_template, filepath)
sone_holder = featurevector.feature_holder(sone_template, filepath)
envelopeHolder = []
audioHolder = []
sonesHolder = []
maxEnvelope = 0;
count =0
print "Feature Extraction Mode\n"
print datetime.now()
# For each chunk of audio
while afm.HasMoreData():
count +=1
audioChunk, chunkIndex = afm.GetNextSegment()
if debug: print "Read %d sample chunk of audio (%0.2fs)" % (len(audioChunk), len(audioChunk) / fs)
# Get Events
eventTimes, envelope = GetEvents(audioChunk, fftParams, debug)
if maxEnvelope < envelope.max():
maxEnvelope = envelope.max()
if debug: print "EVENTTIMES:", eventTimes
envelopeHolder.append(envelope)
eventTimesSamps = np.asarray(np.multiply(eventTimes,fs),dtype=int)
# Get event audio segments
eventSegments = GetEventAudioSegments(eventTimesSamps, audioChunk, debug)
#get sones
eventSegmentSones = GetEventSones(eventSegments, fftParams, debug)
# Get the MFCCs for each segment / event
eventSegmentMFCCs = GetEventMFCCs(eventSegments, fftParams, mfccParams, debug)
# Time-average for each segment / event
averagedEventSegmentMFCCs, averagedEventSegmentSones = AverageEventFeatures(eventSegmentMFCCs, eventSegmentSones, seglen, fftParams, debug)
# Store these vectors in the feature_holder, labelled with their time
StoreFeatureVector(feature_holder, sone_holder, averagedEventSegmentMFCCs, averagedEventSegmentSones, chunkIndex, chunk_len, eventTimes, debug)
# Write features to disk
print datetime.now()
fileSize = feature_holder.save(FEATURE_VECTOR_FILENAME)
print "Wrote", fileSize, "bytes to disk. (%s)" % (FEATURE_VECTOR_FILENAME)
fileSize = sone_holder.save(SONE_VECTOR_FILENAME)
print "Wrote", fileSize, "bytes to disk. (%s)" % (SONE_VECTOR_FILENAME)