def compute(audio, pool, options):
# analysis parameters
sampleRate = options['sampleRate']
frameSize = options['frameSize']
hopSize = options['hopSize']
windowType = options['windowType']
# frame algorithms
frames = essentia.FrameGenerator(audio=audio,
frameSize=frameSize,
hopSize=hopSize)
window = essentia.Windowing(size=frameSize, zeroPadding=0, type=windowType)
spectrum = essentia.Spectrum(size=frameSize)
# spectral algorithms
energy = essentia.Energy()
mfcc = essentia.MFCC(highFrequencyBound=8000)
INFO('Computing Low-Level descriptors necessary for segmentation...')
# used for a nice progress display
total_frames = frames.num_frames()
n_frames = 0
start_of_frame = -frameSize * 0.5
progress = Progress(total=total_frames)
for frame in frames:
frameScope = [
start_of_frame / sampleRate,
(start_of_frame + frameSize) / sampleRate
]
#pool.setCurrentScope(frameScope)
pool.add(namespace + '.' + 'scope', frameScope)
if options['skipSilence'] and essentia.isSilent(frame):
total_frames -= 1
start_of_frame += hopSize
continue
frame_windowed = window(frame)
frame_spectrum = spectrum(frame_windowed)
# need the energy for getting the thumbnail
pool.add(namespace + '.' + 'spectral_energy', energy(frame_spectrum))
# mfcc
(frame_melbands, frame_mfcc) = mfcc(frame_spectrum)
pool.add(namespace + '.' + 'spectral_mfcc', frame_mfcc)
# display of progress report
progress.update(n_frames)
n_frames += 1
start_of_frame += hopSize
progress.finish()
def compute(audio):
audio = essentia.array(audio)
sampleRate = int(conf.opts['sampleRate'])
frameSize = int(conf.opts['frameSize'])
hopSize = int(conf.opts['hopSize'])
zeroPadding = int(conf.opts['zeroPadding'])
windowType = conf.opts['windowType']
frameRate = float(sampleRate) / float(hopSize)
INFO('Computing Ess Detection...')
frames = FrameGenerator(audio=audio, frameSize=frameSize, hopSize=hopSize)
window = Windowing(size=frameSize,
zeroPadding=zeroPadding,
type=windowType)
fft = FFT()
cartesian2polar = CartesianToPolar()
onsetdetectionHFC = OnsetDetection(method="hfc", sampleRate=sampleRate)
onsetdetectionComplex = OnsetDetection(method="complex",
sampleRate=sampleRate)
total_frames = frames.num_frames()
n_frames = 0
start_of_frame = -frameSize * 0.5
hfc = []
complex = []
progress = Progress(total=total_frames)
maxhfc = 0
for frame in frames:
windowed_frame = window(frame)
complex_fft = fft(windowed_frame)
(spectrum, phase) = cartesian2polar(complex_fft)
hfc.append(onsetdetectionHFC(spectrum, phase))
maxhfc = max(hfc[-1], maxhfc)
complex.append(onsetdetectionComplex(spectrum, phase))
# display of progress report
progress.update(n_frames)
n_frames += 1
start_of_frame += hopSize
# The onset rate is defined as the number of onsets per seconds
res = [[x / maxhfc for x in hfc]]
res += [complex]
return np.array(res)
def compute(audio):
audio = essentia.array(audio)
sampleRate = int(conf.opts['sampleRate'])
frameSize = int(conf.opts['frameSize'])
hopSize = int(conf.opts['hopSize'])
zeroPadding = int(conf.opts['zeroPadding'])
windowType = conf.opts['windowType']
frameRate = float(sampleRate) / float(hopSize)
INFO('Computing Onset Detection...')
frames = FrameGenerator(audio=audio, frameSize=frameSize, hopSize=hopSize)
window = Windowing(size=frameSize,
zeroPadding=zeroPadding,
type=windowType)
nsdff = Nsdf()
fftf = Spectrum()
crestf = Crest()
instPowf = InstantPower()
total_frames = frames.num_frames()
n_frames = 0
start_of_frame = -frameSize * 0.5
progress = Progress(total=total_frames)
cr = []
env = []
for frame in frames:
windowed_frame = window(frame)
nsdf = nsdff(frame)
fftn = fftf(nsdf)
cr += [crestf(fftn)]
pow = instPowf(frame)
if len(cr) > 2 and pow < opts["minthresh"]:
cr[-1] = cr[-2]
n_frames += 1
start_of_frame += hopSize
cr = np.array(cr)
# w = signal.gaussian(3,1)
# area = np.sum(w)
# cr =np.convolve(cr,w , 'same')
# cr = cr/(100.*area)
return cr
def compute(audio, pool, options):
# analysis parameters
sampleRate = options['sampleRate']
frameSize = options['frameSize']
hopSize = options['hopSize']
windowType = options['windowType']
# temporal descriptors
lpc = ess.LPC(order=10, type='warped', sampleRate=sampleRate)
zerocrossingrate = ess.ZeroCrossingRate()
# frame algorithms
frames = ess.FrameGenerator(audio=audio, frameSize=frameSize, hopSize=hopSize)
window = ess.Windowing(size=frameSize, zeroPadding=0, type=windowType)
spectrum = ess.Spectrum(size=frameSize)
# spectral algorithms
barkbands = ess.BarkBands(sampleRate=sampleRate)
centralmoments = ess.CentralMoments()
crest = ess.Crest()
centroid = ess.Centroid()
decrease = ess.Decrease()
spectral_contrast = ess.SpectralContrast(frameSize=frameSize,
sampleRate=sampleRate,
numberBands=6,
lowFrequencyBound=20,
highFrequencyBound=11000,
neighbourRatio=0.4,
staticDistribution=0.15)
distributionshape = ess.DistributionShape()
energy = ess.Energy()
# energyband_bass, energyband_middle and energyband_high parameters come from "standard" hi-fi equalizers
energyband_bass = ess.EnergyBand(startCutoffFrequency=20.0, stopCutoffFrequency=150.0, sampleRate=sampleRate)
energyband_middle_low = ess.EnergyBand(startCutoffFrequency=150.0, stopCutoffFrequency=800.0, sampleRate=sampleRate)
energyband_middle_high = ess.EnergyBand(startCutoffFrequency=800.0, stopCutoffFrequency=4000.0,
sampleRate=sampleRate)
energyband_high = ess.EnergyBand(startCutoffFrequency=4000.0, stopCutoffFrequency=20000.0, sampleRate=sampleRate)
flatnessdb = ess.FlatnessDB()
flux = ess.Flux()
harmonic_peaks = ess.HarmonicPeaks()
hfc = ess.HFC()
mfcc = ess.MFCC()
rolloff = ess.RollOff()
rms = ess.RMS()
strongpeak = ess.StrongPeak()
# pitch algorithms
pitch_detection = ess.PitchYinFFT(frameSize=frameSize, sampleRate=sampleRate)
pitch_salience = ess.PitchSalience()
# dissonance
spectral_peaks = ess.SpectralPeaks(sampleRate=sampleRate, orderBy='frequency')
dissonance = ess.Dissonance()
# spectral complexity
# magnitudeThreshold = 0.005 is hardcoded for a "blackmanharris62" frame
spectral_complexity = ess.SpectralComplexity(magnitudeThreshold=0.005)
INFO('Computing Low-Level descriptors...')
# used for a nice progress display
total_frames = frames.num_frames()
n_frames = 0
start_of_frame = -frameSize * 0.5
pitches, pitch_confidences = [], []
progress = Progress(total=total_frames)
#scPool = es.Pool() # pool for spectral contrast
for frame in frames:
frameScope = [start_of_frame / sampleRate, (start_of_frame + frameSize) / sampleRate]
# pool.setCurrentScope(frameScope)
# silence rate
# pool.add(namespace + '.' + 'silence_rate_60dB', es.isSilent(frame))
pool.add(namespace + '.' + 'silence_rate_60dB', is_silent_threshold(frame, -60))
pool.add(namespace + '.' + 'silence_rate_30dB', is_silent_threshold(frame, -30))
pool.add(namespace + '.' + 'silence_rate_20dB', is_silent_threshold(frame, -20))
if options['skipSilence'] and es.isSilent(frame):
total_frames -= 1
start_of_frame += hopSize
continue
# temporal descriptors
pool.add(namespace + '.' + 'zerocrossingrate', zerocrossingrate(frame))
(frame_lpc, frame_lpc_reflection) = lpc(frame)
pool.add(namespace + '.' + 'temporal_lpc', frame_lpc)
frame_windowed = window(frame)
frame_spectrum = spectrum(frame_windowed)
# spectrum-based descriptors
power_spectrum = frame_spectrum ** 2
pool.add(namespace + '.' + 'spectral_centroid', centroid(power_spectrum))
pool.add(namespace + '.' + 'spectral_decrease', decrease(power_spectrum))
pool.add(namespace + '.' + 'spectral_energy', energy(frame_spectrum))
pool.add(namespace + '.' + 'spectral_energyband_low', energyband_bass(frame_spectrum))
pool.add(namespace + '.' + 'spectral_energyband_middle_low', energyband_middle_low(frame_spectrum))
pool.add(namespace + '.' + 'spectral_energyband_middle_high', energyband_middle_high(frame_spectrum))
pool.add(namespace + '.' + 'spectral_energyband_high', energyband_high(frame_spectrum))
pool.add(namespace + '.' + 'hfc', hfc(frame_spectrum))
pool.add(namespace + '.' + 'spectral_rms', rms(frame_spectrum))
pool.add(namespace + '.' + 'spectral_flux', flux(frame_spectrum))
pool.add(namespace + '.' + 'spectral_rolloff', rolloff(frame_spectrum))
pool.add(namespace + '.' + 'spectral_strongpeak', strongpeak(frame_spectrum))
# central moments descriptors
frame_centralmoments = centralmoments(power_spectrum)
(frame_spread, frame_skewness, frame_kurtosis) = distributionshape(frame_centralmoments)
pool.add(namespace + '.' + 'spectral_kurtosis', frame_kurtosis)
pool.add(namespace + '.' + 'spectral_spread', frame_spread)
pool.add(namespace + '.' + 'spectral_skewness', frame_skewness)
# dissonance
(frame_frequencies, frame_magnitudes) = spectral_peaks(frame_spectrum)
frame_dissonance = dissonance(frame_frequencies, frame_magnitudes)
pool.add(namespace + '.' + 'dissonance', frame_dissonance)
# mfcc
(frame_melbands, frame_mfcc) = mfcc(frame_spectrum)
pool.add(namespace + '.' + 'mfcc', frame_mfcc)
# spectral contrast
(sc_coeffs, sc_valleys) = spectral_contrast(frame_spectrum)
#scPool.add(namespace + '.' + 'sccoeffs', sc_coeffs)
#scPool.add(namespace + '.' + 'scvalleys', sc_valleys)
pool.add(namespace + '.' + 'spectral_contrast', sc_coeffs)
# barkbands-based descriptors
frame_barkbands = barkbands(frame_spectrum)
pool.add(namespace + '.' + 'barkbands', frame_barkbands)
pool.add(namespace + '.' + 'spectral_crest', crest(frame_barkbands))
pool.add(namespace + '.' + 'spectral_flatness_db', flatnessdb(frame_barkbands))
barkbands_centralmoments = ess.CentralMoments(range=len(frame_barkbands) - 1)
(barkbands_spread, barkbands_skewness, barkbands_kurtosis) = distributionshape(
barkbands_centralmoments(frame_barkbands))
pool.add(namespace + '.' + 'barkbands_spread', barkbands_spread)
pool.add(namespace + '.' + 'barkbands_skewness', barkbands_skewness)
pool.add(namespace + '.' + 'barkbands_kurtosis', barkbands_kurtosis)
# pitch descriptors
frame_pitch, frame_pitch_confidence = pitch_detection(frame_spectrum)
if frame_pitch > 0 and frame_pitch <= 20000.:
pool.add(namespace + '.' + 'pitch', frame_pitch)
pitches.append(frame_pitch)
pitch_confidences.append(frame_pitch_confidence)
pool.add(namespace + '.' + 'pitch_instantaneous_confidence', frame_pitch_confidence)
frame_pitch_salience = pitch_salience(frame_spectrum[:-1])
pool.add(namespace + '.' + 'pitch_salience', frame_pitch_salience)
# spectral complexity
pool.add(namespace + '.' + 'spectral_complexity', spectral_complexity(frame_spectrum))
# display of progress report
progress.update(n_frames)
n_frames += 1
start_of_frame += hopSize
# if no 'temporal_zerocrossingrate' it means that this is a silent file
if 'zerocrossingrate' not in descriptorNames(pool.descriptorNames(), namespace):
raise ess.EssentiaError('This is a silent file!')
#spectralContrastPCA(scPool, pool)
# build pitch value histogram
from math import log
from numpy import bincount
# convert from Hz to midi notes
midipitches = []
unknown = 0
for freq in pitches:
if freq > 0. and freq <= 12600:
midipitches.append(12 * (log(freq / 6.875) / 0.69314718055995) - 3.)
else:
unknown += 1
if len(midipitches) > 0:
# compute histogram
midipitchhist = bincount(midipitches)
# set 0 midi pitch to be the number of pruned value
midipitchhist[0] = unknown
# normalise
midipitchhist = [val / float(sum(midipitchhist)) for val in midipitchhist]
# zero pad
for i in range(128 - len(midipitchhist)): midipitchhist.append(0.0)
else:
midipitchhist = [0.] * 128
midipitchhist[0] = 1.
# pitchhist = ess.array(zip(range(len(midipitchhist)), midipitchhist))
pool.add(namespace + '.' + 'spectral_pitch_histogram', midipitchhist) # , pool.GlobalScope)
# the code below is the same as the one above:
# for note in midipitchhist:
# pool.add(namespace + '.' + 'spectral_pitch_histogram_values', note)
# print "midi note:", note
pitch_centralmoments = ess.CentralMoments(range=len(midipitchhist) - 1)
(pitch_histogram_spread, pitch_histogram_skewness, pitch_histogram_kurtosis) = distributionshape(
pitch_centralmoments(midipitchhist))
pool.add(namespace + '.' + 'spectral_pitch_histogram_spread', pitch_histogram_spread) # , pool.GlobalScope)
progress.finish()
def compute(audio, pool, options):
# analysis parameters
sampleRate = options['sampleRate']
frameSize = options['frameSize']
hopSize = options['hopSize']
windowType = options['windowType']
# frame algorithms
frames = essentia.FrameGenerator(audio=audio,
frameSize=frameSize,
hopSize=hopSize,
startFromZero=True)
loudness = essentia.Loudness()
INFO('Computing Dynamic descriptors...')
# used for a nice progress display
total_frames = frames.num_frames()
n_frames = 0
level_array = []
progress = Progress(total=total_frames)
for frame in frames:
frame_level = loudness(frame)
level_array.append(frame_level)
# display of progress report
progress.update(n_frames)
n_frames += 1
# Maximum dynamic
EPSILON = 10e-6
max_value = max(level_array)
if max_value <= EPSILON:
max_value = EPSILON
# Normalization to the maximum
THRESHOLD = 0.0001 # this corresponds to -80dB
for i in range(len(level_array)):
level_array[i] /= max_value
if level_array[i] <= THRESHOLD:
level_array[i] = THRESHOLD
# Dynamic Average
mean = essentia.Mean()
average_loudness = 10.0 * log10(mean(level_array))
# re-scaling and range-control
# This yields in numbers between
#
# 0 for signals with large dynamic variace and
# thus low dynamic average
# 1 for signal with little dynamic range and thus
# a dynamic average close to the maximum
# TO DO: [0, 0] should be pool.GlobalScope
average_loudness_within_zero_to_one = squeezeInto([-5, 0], [-2, 1],
average_loudness)
pool.add(namespace + "." + "average_loudness",
average_loudness_within_zero_to_one) #, pool.GlobalScope)
# Dynamic Fluctuation
'''
variance = essentia.Variance()
level_variance = variance(level_array)
if level_variance <= THRESHOLD:
level_variance = THRESHOLD
level_fluctuation = 10*log10(level_variance)
# TO DO: [0, 0] should be pool.GlobalScope
pool.add("level_fluctuation", level_fluctuation, pool.GlobalScope)
'''
INFO('\r100% done...')
def compute(audio, pool, options):
INFO('Computing Tonal descriptors...')
sampleRate = options['sampleRate']
frameSize = options['frameSize']
hopSize = options['hopSize']
zeroPadding = options['zeroPadding']
windowType = options['windowType']
frames = essentia.FrameGenerator(audio=audio,
frameSize=frameSize,
hopSize=hopSize)
window = essentia.Windowing(size=frameSize,
zeroPadding=zeroPadding,
type=windowType)
spectrum = essentia.Spectrum(size=(frameSize + zeroPadding) / 2)
spectral_peaks = essentia.SpectralPeaks(maxPeaks=10000,
magnitudeThreshold=0.00001,
minFrequency=40,
maxFrequency=5000,
orderBy="frequency")
tuning = essentia.TuningFrequency()
# computing the tuning frequency
tuning_frequency = 440.0
for frame in frames:
frame_windowed = window(frame)
frame_spectrum = spectrum(frame_windowed)
(frame_frequencies, frame_magnitudes) = spectral_peaks(frame_spectrum)
#if len(frame_frequencies) > 0:
(tuning_frequency, tuning_cents) = tuning(frame_frequencies,
frame_magnitudes)
pool.add(namespace + '.' + 'tuning_frequency',
tuning_frequency) #, pool.GlobalScope)
# computing the HPCPs
spectral_whitening = essentia.SpectralWhitening()
hpcp_key_size = 36
hpcp_chord_size = 36
hpcp_tuning_size = 120
hpcp_key = essentia.HPCP(size=hpcp_key_size,
referenceFrequency=tuning_frequency,
bandPreset=False,
minFrequency=40.0,
maxFrequency=5000.0,
weightType='squaredCosine',
nonLinear=False,
windowSize=4.0 / 3.0,
sampleRate=sampleRate)
hpcp_chord = essentia.HPCP(size=hpcp_chord_size,
referenceFrequency=tuning_frequency,
harmonics=8,
bandPreset=True,
minFrequency=40.0,
maxFrequency=5000.0,
splitFrequency=500.0,
weightType='cosine',
nonLinear=True,
windowSize=0.5,
sampleRate=sampleRate)
hpcp_tuning = essentia.HPCP(size=hpcp_tuning_size,
referenceFrequency=tuning_frequency,
harmonics=8,
bandPreset=True,
minFrequency=40.0,
maxFrequency=5000.0,
splitFrequency=500.0,
weightType='cosine',
nonLinear=True,
windowSize=0.5,
sampleRate=sampleRate)
# intializing the HPCP arrays
hpcps_key = []
hpcps_chord = []
hpcps_tuning = []
# computing HPCP loop
frames = essentia.FrameGenerator(audio=audio,
frameSize=frameSize,
hopSize=hopSize)
total_frames = frames.num_frames()
n_frames = 0
start_of_frame = -frameSize * 0.5
progress = Progress(total=total_frames)
for frame in frames:
#frameScope = [ start_of_frame / sampleRate, (start_of_frame + frameSize) / sampleRate ]
#pool.setCurrentScope(frameScope)
if options['skipSilence'] and essentia.isSilent(frame):
total_frames -= 1
start_of_frame += hopSize
continue
frame_windowed = window(frame)
frame_spectrum = spectrum(frame_windowed)
# spectral peaks
(frame_frequencies, frame_magnitudes) = spectral_peaks(frame_spectrum)
if (len(frame_frequencies) > 0):
# spectral_whitening
frame_magnitudes_white = spectral_whitening(
frame_spectrum, frame_frequencies, frame_magnitudes)
frame_hpcp_key = hpcp_key(frame_frequencies,
frame_magnitudes_white)
frame_hpcp_chord = hpcp_chord(frame_frequencies,
frame_magnitudes_white)
frame_hpcp_tuning = hpcp_tuning(frame_frequencies,
frame_magnitudes_white)
else:
frame_hpcp_key = essentia.array([0] * hpcp_key_size)
frame_hpcp_chord = essentia.array([0] * hpcp_chord_size)
frame_hpcp_tuning = essentia.array([0] * hpcp_tuning_size)
# key HPCP
hpcps_key.append(frame_hpcp_key)
# add HPCP to the pool
pool.add(namespace + '.' + 'hpcp', frame_hpcp_key)
# chords HPCP
hpcps_chord.append(frame_hpcp_chord)
# tuning system HPCP
hpcps_tuning.append(frame_hpcp_tuning)
# display of progress report
progress.update(n_frames)
n_frames += 1
start_of_frame += hopSize
progress.finish()
# check if silent file
if len(hpcps_key) == 0:
raise EssentiaError('This is a silent file!')
# key detection
key_detector = essentia.Key(profileType='temperley')
average_hpcps_key = numpy.average(essentia.array(hpcps_key), axis=0)
average_hpcps_key = normalize(average_hpcps_key)
# thpcps
max_arg = numpy.argmax(average_hpcps_key)
thpcp = []
for i in range(max_arg, len(average_hpcps_key)):
thpcp.append(float(average_hpcps_key[i]))
for i in range(max_arg):
thpcp.append(float(average_hpcps_key[i]))
pool.add(namespace + '.' + 'thpcp', thpcp) #, pool.GlobalScope )
(key, scale, key_strength,
first_to_second_relative_strength) = key_detector(
essentia.array(average_hpcps_key))
pool.add(namespace + '.' + 'key_key', key) #, pool.GlobalScope)
pool.add(namespace + '.' + 'key_scale', scale) #, pool.GlobalScope)
pool.add(namespace + '.' + 'key_strength',
key_strength) #, pool.GlobalScope)
# chord detection
chord_detector = essentia.Key(profileType='tonictriad', usePolyphony=False)
hpcp_frameSize = 2.0 # 2 seconds
hpcp_number = int(hpcp_frameSize * (sampleRate / hopSize - 1))
for hpcp_index in range(len(hpcps_chord)):
hpcp_index_begin = max(0, hpcp_index - hpcp_number)
hpcp_index_end = min(hpcp_index + hpcp_number, len(hpcps_chord))
average_hpcps_chord = numpy.average(essentia.array(
hpcps_chord[hpcp_index_begin:hpcp_index_end]),
axis=0)
average_hpcps_chord = normalize(average_hpcps_chord)
(key, scale, strength,
first_to_second_relative_strength) = chord_detector(
essentia.array(average_hpcps_chord))
if scale == 'minor':
chord = key + 'm'
else:
chord = key
frame_second_scope = [
hpcp_index_begin * hopSize / sampleRate,
hpcp_index_end * hopSize / sampleRate
]
pool.add(namespace + '.' + 'chords_progression',
chord) #, frame_second_scope)
pool.add(namespace + '.' + 'chords_strength',
strength) #, frame_second_scope)
# tuning system features
keydetector = essentia.Key(profileType='diatonic')
average_hpcps_tuning = numpy.average(essentia.array(hpcps_tuning), axis=0)
average_hpcps_tuning = normalize(average_hpcps_tuning)
(key, scale, diatonic_strength,
first_to_second_relative_strength) = keydetector(
essentia.array(average_hpcps_tuning))
pool.add(namespace + '.' + 'tuning_diatonic_strength',
diatonic_strength) #, pool.GlobalScope)
(equal_tempered_deviation, nontempered_energy_ratio,
nontempered_peaks_energy_ratio
) = essentia.HighResolutionFeatures()(average_hpcps_tuning)
pool.add(namespace + '.' + 'tuning_equal_tempered_deviation',
equal_tempered_deviation) #, pool.GlobalScope)
pool.add(namespace + '.' + 'tuning_nontempered_energy_ratio',
nontempered_energy_ratio) #, pool.GlobalScope)
pool.add(namespace + '.' + 'tuning_nontempered_peaks_energy_ratio',
nontempered_peaks_energy_ratio) #, pool.GlobalScope)
def compute(audio, pool, options):
sampleRate = options['sampleRate']
frameSize = options['frameSize']
hopSize = options['hopSize']
zeroPadding = options['zeroPadding']
windowType = options['windowType']
frameRate = float(sampleRate) / float(frameSize - hopSize)
INFO('Computing Onset Detection...')
frames = essentia.FrameGenerator(audio=audio,
frameSize=frameSize,
hopSize=hopSize)
window = essentia.Windowing(size=frameSize,
zeroPadding=zeroPadding,
type=windowType)
fft = essentia.FFT()
cartesian2polar = essentia.CartesianToPolar()
onsetdetectionHFC = essentia.OnsetDetection(method="hfc",
sampleRate=sampleRate)
onsetdetectionComplex = essentia.OnsetDetection(method="complex",
sampleRate=sampleRate)
onsets = essentia.Onsets(frameRate=frameRate)
total_frames = frames.num_frames()
n_frames = 0
start_of_frame = -frameSize * 0.5
hfc = []
complex = []
progress = Progress(total=total_frames)
for frame in frames:
if essentia.instantPower(frame) < 1.e-4:
total_frames -= 1
start_of_frame += hopSize
hfc.append(0.)
complex.append(0.)
continue
windowed_frame = window(frame)
complex_fft = fft(windowed_frame)
(spectrum, phase) = cartesian2polar(complex_fft)
hfc.append(onsetdetectionHFC(spectrum, phase))
complex.append(onsetdetectionComplex(spectrum, phase))
# display of progress report
progress.update(n_frames)
n_frames += 1
start_of_frame += hopSize
# The onset rate is defined as the number of onsets per seconds
detections = numpy.concatenate(
[essentia.array([hfc]),
essentia.array([complex])])
# prune all 'doubled' detections
time_onsets = list(onsets(detections, essentia.array([1, 1])))
t = 1
while t < len(time_onsets):
if time_onsets[t] - time_onsets[t - 1] < 0.080: time_onsets.pop(t)
else: t += 1
onsetrate = len(time_onsets) / (len(audio) / sampleRate)
pool.add(namespace + '.' + "onset_times",
essentia.array(time_onsets)) #, pool.GlobalScope)
pool.add(namespace + '.' + "onset_rate", onsetrate) #, pool.GlobalScope)
progress.finish()
def compute(audio, pool, options):
INFO("Computing Beats descriptors...")
sampleRate = options['sampleRate']
windowType = options['windowType']
beat_window_duration = 0.1 # 100ms
beat_duration = 0.05 # 50ms estimation after checking some drums kicks duration on freesound
beats = pool.value('rhythm.beats_position')[0]
# special case
if len(beats) == 0:
# we add them 2 times to get 'mean/var' stats and not 'value'
# and not on full scope so it's not global
# FIXME: should use "undefined"
pool.add("beats_loudness", 0.0, [0., 0.])
pool.add("beats_loudness", 0.0, [0., 0.])
pool.add("beats_loudness_bass", 0.0, [0., 0.])
pool.add("beats_loudness_bass", 0.0, [0., 0.])
INFO('100% done...')
return
duration = pool.value('metadata.duration_processed')[0]
# FIXME: converted to samples in order to have more accurate control of the size of
# the window. This is due to FFT not being able to be computed on arrays of
# odd sizes. Please FIXME later, when FFT accepts all kinds of sizes.
beat_window_duration = int(beat_window_duration * float(sampleRate) + 0.5)
beat_duration = int(beat_duration * float(sampleRate) + 0.5)
duration *= float(sampleRate)
if beat_duration % 2 == 1:
beat_duration += 1
beat_window_duration = beat_duration * 2
energy = essentia.Energy()
energybandratio = essentia.EnergyBandRatio(startFrequency=20.0,
stopFrequency=150.0,
sampleRate=sampleRate)
total_beats = len(beats)
n_beats = 1
progress = Progress(total=total_beats)
between_beats_start = [0.0]
between_beats_end = []
beats_spectral_energy = 0.0
# love on the beats
for beat in beats:
# convert beat to samples in order to ensure an even size
beat = beat * float(sampleRate)
beat_window_start = (beat - beat_window_duration / 2.0) # in samples
beat_window_end = (beat + beat_window_duration / 2.0) # in samples
if beat_window_start > 0.0 and beat_window_end < duration: # in samples
#print "duration: ", duration, "start:", beat_window_start, "end:", beat_window_end
beat_window = audio[beat_window_start:beat_window_end]
beat_start = beat_window_start + max_energy_index(beat_window)
beat_end = beat_start + beat_duration
beat_audio = audio[beat_start:beat_end]
beat_scope = [
beat_start / float(sampleRate), beat_end / float(sampleRate)
] # in seconds
#print "beat audio size: ", len(beat_audio)
window = essentia.Windowing(size=len(beat_audio),
zeroPadding=0,
type=windowType)
spectrum = essentia.Spectrum(size=len(beat_audio))
beat_spectrum = spectrum(window(beat_audio))
beat_spectral_energy = energy(beat_spectrum)
pool.add(namespace + '.' + 'beats_loudness',
beat_spectral_energy) #, beat_scope)
beats_spectral_energy += beat_spectral_energy
beat_spectral_energybandratio = energybandratio(beat_spectrum)
pool.add(namespace + '.' + 'beats_loudness_bass',
beat_spectral_energybandratio) #, beat_scope)
# filling between-beats arrays
between_beats_end.append(beat_start / float(sampleRate))
between_beats_start.append(beat_end / float(sampleRate))
# display of progress report
progress.update(n_beats / float(sampleRate))
n_beats += 1
between_beats_end.append(duration)
between_beats_spectral_energy = 0.0
# love in between beats
'''
for between_beat_start, between_beat_end in zip(between_beats_start, between_beats_end):
between_beat_audio = audio[between_beat_start * sampleRate : between_beat_end * sampleRate]
between_beat_scope = [between_beat_start, between_beat_end]
window = essentia.Windowing(windowSize = len(between_beat_audio), zeroPadding = 0, type = "blackmanharris62")
spectrum = essentia.Spectrum(size = len(between_beat_audio))
between_beat_spectrum = spectrum(window(between_beat_audio))
between_beat_spectral_energy = energy(between_beat_spectrum)
between_beats_spectral_energy += between_beat_spectral_energy
'''
progress.finish()
def compute(audio, pool, options):
INFO('Computing SFX descriptors...')
# analysis parameters
sampleRate = options['sampleRate']
frameSize = options['frameSize']
hopSize = options['hopSize']
windowType = options['windowType']
# frame algorithms
frames = essentia.FrameGenerator(audio=audio,
frameSize=frameSize,
hopSize=hopSize)
window = essentia.Windowing(size=frameSize, zeroPadding=0, type=windowType)
spectrum = essentia.Spectrum(size=frameSize)
# pitch algorithm
pitch_detection = essentia.PitchDetection(frameSize=2048,
sampleRate=sampleRate)
# sfx descriptors
spectral_peaks = essentia.SpectralPeaks(sampleRate=sampleRate,
orderBy='frequency')
harmonic_peaks = essentia.HarmonicPeaks()
inharmonicity = essentia.Inharmonicity()
odd2evenharmonicenergyratio = essentia.OddToEvenHarmonicEnergyRatio()
tristimulus = essentia.Tristimulus()
# used for a nice progress display
total_frames = frames.num_frames()
n_frames = 0
start_of_frame = -frameSize * 0.5
progress = Progress(total=total_frames)
for frame in frames:
frameScope = [
start_of_frame / sampleRate,
(start_of_frame + frameSize) / sampleRate
]
#pool.setCurrentScope(frameScope)
if options['skipSilence'] and essentia.isSilent(frame):
total_frames -= 1
start_of_frame += hopSize
continue
frame_windowed = window(frame)
frame_spectrum = spectrum(frame_windowed)
# pitch descriptors
frame_pitch, frame_pitch_confidence = pitch_detection(frame_spectrum)
# spectral peaks based descriptors
(frame_frequencies, frame_magnitudes) = spectral_peaks(frame_spectrum)
(frame_harmonic_frequencies,
frame_harmonic_magnitudes) = harmonic_peaks(frame_frequencies,
frame_magnitudes,
frame_pitch)
if len(frame_harmonic_frequencies) > 1:
frame_inharmonicity = inharmonicity(frame_harmonic_frequencies,
frame_harmonic_magnitudes)
pool.add(namespace + '.' + 'inharmonicity', frame_inharmonicity)
frame_tristimulus = tristimulus(frame_harmonic_frequencies,
frame_harmonic_magnitudes)
pool.add(namespace + '.' + 'tristimulus', frame_tristimulus)
frame_odd2evenharmonicenergyratio = odd2evenharmonicenergyratio(
frame_harmonic_frequencies, frame_harmonic_magnitudes)
pool.add(namespace + '.' + 'odd2evenharmonicenergyratio',
frame_odd2evenharmonicenergyratio)
# display of progress report
progress.update(n_frames)
n_frames += 1
start_of_frame += hopSize
envelope = essentia.Envelope()
file_envelope = envelope(audio)
# temporal statistics
decrease = essentia.AudioDecrease(blockSize=len(audio))
pool.add(namespace + '.' + 'temporal_decrease',
decrease(file_envelope)) #, pool.GlobalScope)
centralmoments = essentia.AudioCentralMoments(blockSize=len(audio))
file_centralmoments = centralmoments(file_envelope)
distributionshape = essentia.DistributionShape()
(file_spread, file_skewness,
file_kurtosis) = distributionshape(file_centralmoments)
pool.add(namespace + '.' + 'temporal_spread',
file_spread) #, pool.GlobalScope)
pool.add(namespace + '.' + 'temporal_skewness',
file_skewness) #, pool.GlobalScope)
pool.add(namespace + '.' + 'temporal_kurtosis',
file_kurtosis) #, pool.GlobalScope)
centroid = essentia.AudioCentroid(blockSize=len(audio))
pool.add(namespace + '.' + 'temporal_centroid',
centroid(file_envelope)) #, pool.GlobalScope)
# effective duration
effectiveduration = essentia.EffectiveDuration()
pool.add(namespace + '.' + 'effective_duration',
effectiveduration(file_envelope)) #, pool.GlobalScope)
# log attack time
logattacktime = essentia.LogAttackTime()
pool.add(namespace + '.' + 'logattacktime',
logattacktime(audio)) #, pool.GlobalScope)
# strong decay
strongdecay = essentia.StrongDecay()
pool.add(namespace + '.' + 'strongdecay',
strongdecay(file_envelope)) #, pool.GlobalScope)
# dynamic profile
flatness = essentia.FlatnessSFX()
pool.add(namespace + '.' + 'flatness',
flatness(file_envelope)) #, pool.GlobalScope)
# onsets number
onsets_number = len(pool.value('rhythm.onset_times')[0])
pool.add(namespace + '.' + 'onsets_number',
onsets_number) #, pool.GlobalScope)
# morphological descriptors
max_to_total = essentia.MaxToTotal()
pool.add(namespace + '.' + 'max_to_total',
max_to_total(file_envelope)) #, pool.GlobalScope)
tc_to_total = essentia.TCToTotal(sampleRate=sampleRate)
pool.add(namespace + '.' + 'tc_to_total',
tc_to_total(file_envelope)) #, pool.GlobalScope)
derivativeSFX = essentia.DerivativeSFX(sampleRate=sampleRate)
(der_av_after_max, max_der_before_max) = derivativeSFX(file_envelope)
pool.add(namespace + '.' + 'der_av_after_max',
der_av_after_max) #, pool.GlobalScope)
pool.add(namespace + '.' + 'max_der_before_max',
max_der_before_max) #, pool.GlobalScope)
# pitch profile
pitch = pool.value('lowlevel.pitch')
if len(pitch) > 1:
pool.add(namespace + '.' + 'pitch_max_to_total',
max_to_total(pitch)) #, pool.GlobalScope)
min_to_total = essentia.MinToTotal()
pool.add(namespace + '.' + 'pitch_min_to_total',
min_to_total(pitch)) #, pool.GlobalScope)
pitch_centroid = essentia.Centroid(range=len(pitch) - 1)
pool.add(namespace + '.' + 'pitch_centroid',
pitch_centroid(pitch)) #, pool.GlobalScope)
pitch_after_max_to_before_max_energy_ratio = essentia.AfterMaxToBeforeMaxEnergyRatio(
)
pool.add(namespace + '.' +
'pitch_after_max_to_before_max_energy_ratio',
pitch_after_max_to_before_max_energy_ratio(
pitch)) #, pool.GlobalScope)
else:
pool.add(namespace + '.' + 'pitch_max_to_total',
0.0) #, pool.GlobalScope)
pool.add(namespace + '.' + 'pitch_min_to_total',
0.0) #, pool.GlobalScope)
pool.add(namespace + '.' + 'pitch_centroid', 0.0) #, pool.GlobalScope)
pool.add(namespace + '.' +
'pitch_after_max_to_before_max_energy_ratio',
0.0) #, pool.GlobalScope)
progress.finish()