def HPFilter(audio, cutoff):
HPF = es.HighPass(cutoffFrequency=cutoff)
filtered_audio = HPF(audio)
writer = es.MonoWriter(filename='holst_test.wav')
writer(filtered_audio)
return filtered_audio
def filter_loops():
loops = os.listdir(CHOPPED_PATH)
proc_loops = os.listdir(EQ_NEW_PATH)
lp_filter = es.LowPass(cutoffFrequency=90,sampleRate=sampleRate)
bp_filter = es.BandPass(bandwidth=100 ,cutoffFrequency=280,sampleRate=sampleRate)
hp_filter = es.HighPass(cutoffFrequency=9000,sampleRate=sampleRate)
i=0
for loop in loops:
i=i+1
if i % 50 == 0:
print(str(i))
if ".wav" in loop:
if ("bpf_" + loop) not in proc_loops:
audio_file=es.MonoLoader(filename=CHOPPED_PATH+loop,sampleRate=sampleRate)
#lpf_audio = lp_filter(audio_file())
bpf_audio = bp_filter(audio_file())
#hpf_audio = hp_filter(audio_file())
#sf.write(EQ_PATH + "lpf_" + loop, lpf_audio, sampleRate)
sf.write(EQ_NEW_PATH + "bpf_" + loop, bpf_audio, sampleRate)
def filter_loops_eval():
loops_paths = [ "icassp2021_outputs/outputs_stft_coherence/",
"icassp2021_outputs/outputs_wavstft_coherence/"]
lp_filter = es.LowPass(cutoffFrequency=90,sampleRate=sampleRate)
bp_filter = es.BandPass(bandwidth=100 ,cutoffFrequency=280,sampleRate=sampleRate)
hp_filter = es.HighPass(cutoffFrequency=9000,sampleRate=sampleRate)
for path in loops_paths:
loops = os.listdir(path)
for loop in loops:
if ".wav" in loop:
audio_file=es.MonoLoader(filename=path+loop,sampleRate=sampleRate)
if "lpf" in loop:
lpf_audio = lp_filter(audio_file())
sf.write(path + "eq/" + loop, lpf_audio, sampleRate)
if "bpf" in loop:
bpf_audio = bp_filter(audio_file())
sf.write(path + "eq/" + loop, bpf_audio, sampleRate)
if "hpf" in loop:
hpf_audio = hp_filter(audio_file())
sf.write(path + "eq/" + loop, hpf_audio, sampleRate)
import essentia.standard as ess
import numpy as np
import pickle
import glob
import utilFunctions as UF
import scipy.spatial.distance as DS
import parameters as params
import csv
rms=ess.RMS()
window = ess.Windowing(type = "hamming")
spec = ess.Spectrum(size=params.Nfft)
zz = np.zeros((params.zeropadLen,), dtype = 'float32')
genmfcc = ess.MFCC(highFrequencyBound = 22000.0, inputSize = params.Nfft/2+1, sampleRate = params.Fs)
hps = ess.HighPass(cutoffFrequency = 240.0)
onsets = ess.Onsets()
strokeLabels = ['dha', 'dhen', 'dhi', 'dun', 'ge', 'kat', 'ke', 'na', 'ne', 're', 'tak', 'te', 'tit', 'tun']
taals = {"teen": {"nmatra": 16, "accents": np.array([4, 1, 1, 1, 3, 1, 1, 1, 2, 1, 1, 1, 3, 1, 1, 1])},
"ek": {"nmatra": 12, "accents": np.array([4, 1, 1, 2, 1, 1, 3, 1, 1, 2, 1, 1])},
"jhap": {"nmatra": 10, "accents": np.array([4, 1, 2, 1, 1, 3, 1, 2, 1, 1])},
"rupak": {"nmatra": 7, "accents": np.array([2, 1, 1, 3, 1, 3, 1])}
}
rolls = [{"bol": ['dha/dha_02', 'te/te_05', 're/re_04', 'dha/dha_02'], "dur": np.array([1.0, 1.0, 1, 1]), "amp": np.array([1.0, 1.0, 1.0, 1.0])},
{"bol": ['te/te_02', 're/re_05', 'ke/ke_04', 'te/te_02'], "dur": np.array([1.0, 1.0, 1, 1]), "amp": np.array([1.0, 1.0, 1.0, 1.0])},
{"bol": ['ge/ge_02', 'ge/ge_05', 'te/te_04', 'te/te_02'], "dur": np.array([1.0, 1.0, 1, 1]), "amp": np.array([1.0, 1.0, 1.0, 1.0])},
{"bol": ['ge/ge_02', 'ge/ge_05', 'dhi/dhi_04', 'na/na_02'], "dur": np.array([1.0, 1.0, 1, 1]), "amp": np.array([1.0, 1.0, 1.0, 1.0])},
{"bol": ['dha/dha_02', 'dha/dha_02', 'te/te_05', 'te/te_06'], "dur": np.array([1.0, 1.0, 1, 1]), "amp": np.array([1.0, 1.0, 1.0, 1.0])},
def estimate_key(input_audio_file, output_text_file=None, key_profile=None):
"""
This function estimates the overall key of an audio track
optionaly with extra modal information.
:type input_audio_file: str
:type output_text_file: str
"""
if key_profile is not None:
global USE_THREE_PROFILES
global WITH_MODAL_DETAILS
global KEY_PROFILE
KEY_PROFILE = key_profile
USE_THREE_PROFILES = False
WITH_MODAL_DETAILS = False
loader = estd.MonoLoader(filename=input_audio_file, sampleRate=SAMPLE_RATE)
cut = estd.FrameCutter(frameSize=WINDOW_SIZE, hopSize=HOP_SIZE)
window = estd.Windowing(size=WINDOW_SIZE, type=WINDOW_SHAPE)
rfft = estd.Spectrum(size=WINDOW_SIZE)
sw = estd.SpectralWhitening(maxFrequency=MAX_HZ, sampleRate=SAMPLE_RATE)
speaks = estd.SpectralPeaks(magnitudeThreshold=SPECTRAL_PEAKS_THRESHOLD,
maxFrequency=MAX_HZ,
minFrequency=MIN_HZ,
maxPeaks=SPECTRAL_PEAKS_MAX,
sampleRate=SAMPLE_RATE)
hpcp = estd.HPCP(
bandPreset=HPCP_BAND_PRESET,
#bandSplitFrequency=HPCP_SPLIT_HZ,
harmonics=HPCP_HARMONICS,
maxFrequency=MAX_HZ,
minFrequency=MIN_HZ,
nonLinear=HPCP_NON_LINEAR,
normalized=HPCP_NORMALIZE,
referenceFrequency=HPCP_REFERENCE_HZ,
sampleRate=SAMPLE_RATE,
size=HPCP_SIZE,
weightType=HPCP_WEIGHT_TYPE,
windowSize=HPCP_WEIGHT_WINDOW_SEMITONES,
maxShifted=HPCP_SHIFT)
if HIGHPASS_CUTOFF is not None:
hpf = estd.HighPass(cutoffFrequency=HIGHPASS_CUTOFF,
sampleRate=SAMPLE_RATE)
audio = hpf(hpf(hpf(loader())))
else:
audio = loader()
duration = len(audio)
n_slices = 1 + (duration // HOP_SIZE)
chroma = np.empty([n_slices, HPCP_SIZE], dtype='float64')
for slice_n in range(n_slices):
spek = rfft(window(cut(audio)))
p1, p2 = speaks(spek)
if SPECTRAL_WHITENING:
p2 = sw(spek, p1, p2)
pcp = hpcp(p1, p2)
if not DETUNING_CORRECTION or DETUNING_CORRECTION_SCOPE == 'average':
chroma[slice_n] = pcp
elif DETUNING_CORRECTION and DETUNING_CORRECTION_SCOPE == 'frame':
pcp = shift_pcp(pcp, HPCP_SIZE)
chroma[slice_n] = pcp
else:
raise NameError("SHIFT_SCOPE must be set to 'frame' or 'average'.")
chroma = np.sum(chroma, axis=0)
if PCP_THRESHOLD is not None:
chroma = normalize_pcp_peak(chroma)
chroma = pcp_gate(chroma, PCP_THRESHOLD)
if DETUNING_CORRECTION and DETUNING_CORRECTION_SCOPE == 'average':
chroma = shift_pcp(chroma, HPCP_SIZE)
chroma = np.roll(
chroma, -3) # Adjust to essentia's HPCP calculation starting on A...
if USE_THREE_PROFILES:
estimation_1 = template_matching_3(chroma, KEY_PROFILE)
else:
estimation_1 = template_matching_2(chroma, KEY_PROFILE)
key_1 = estimation_1[0] + '\t' + estimation_1[1]
correlation_value = estimation_1[2]
if WITH_MODAL_DETAILS:
estimation_2 = template_matching_modal(chroma)
key_2 = estimation_2[0] + '\t' + estimation_2[1]
key_verbose = key_1 + '\t' + key_2
key = key_verbose.split('\t')
# Assign monotonic tracks to minor:
if key[3] == 'monotonic' and key[0] == key[2]:
key = '{0}\tminor'.format(key[0])
else:
key = key_1
else:
key = key_1
if output_text_file is not None:
textfile = open(output_text_file, 'w')
textfile.write(key + '\t' + str(correlation_value) + '\n')
textfile.close()
return key, correlation_value
def key_aes(input_audio_file, output_text_file, **kwargs):
"""
This function estimates the overall key of an audio track
optionally with extra modal information.
:type input_audio_file: str
:type output_text_file: str
"""
if not kwargs:
kwargs = KEY_SETTINGS
loader = estd.MonoLoader(filename=input_audio_file,
sampleRate=kwargs["SAMPLE_RATE"])
cut = estd.FrameCutter(frameSize=kwargs["WINDOW_SIZE"],
hopSize=kwargs["HOP_SIZE"])
window = estd.Windowing(size=kwargs["WINDOW_SIZE"],
type=kwargs["WINDOW_SHAPE"])
rfft = estd.Spectrum(size=kwargs["WINDOW_SIZE"])
sw = estd.SpectralWhitening(maxFrequency=kwargs["MAX_HZ"],
sampleRate=kwargs["SAMPLE_RATE"])
speaks = estd.SpectralPeaks(
magnitudeThreshold=kwargs["SPECTRAL_PEAKS_THRESHOLD"],
maxFrequency=kwargs["MAX_HZ"],
minFrequency=kwargs["MIN_HZ"],
maxPeaks=kwargs["SPECTRAL_PEAKS_MAX"],
sampleRate=kwargs["SAMPLE_RATE"])
hpcp = estd.HPCP(bandPreset=kwargs["HPCP_BAND_PRESET"],
splitFrequency=kwargs["HPCP_SPLIT_HZ"],
harmonics=kwargs["HPCP_HARMONICS"],
maxFrequency=kwargs["MAX_HZ"],
minFrequency=kwargs["MIN_HZ"],
nonLinear=kwargs["HPCP_NON_LINEAR"],
normalized=kwargs["HPCP_NORMALIZE"],
referenceFrequency=kwargs["HPCP_REFERENCE_HZ"],
sampleRate=kwargs["SAMPLE_RATE"],
size=kwargs["HPCP_SIZE"],
weightType=kwargs["HPCP_WEIGHT_TYPE"],
windowSize=kwargs["HPCP_WEIGHT_WINDOW_SEMITONES"],
maxShifted=kwargs["HPCP_SHIFT"])
audio = loader()
if kwargs["HIGHPASS_CUTOFF"] is not None:
hpf = estd.HighPass(cutoffFrequency=kwargs["HIGHPASS_CUTOFF"],
sampleRate=kwargs["SAMPLE_RATE"])
audio = hpf(hpf(hpf(audio)))
if kwargs["DURATION"] is not None:
audio = audio[(kwargs["START_TIME"] *
kwargs["SAMPLE_RATE"]):(kwargs["DURATION"] *
kwargs["SAMPLE_RATE"])]
duration = len(audio)
number_of_frames = int(duration / kwargs["HOP_SIZE"])
chroma = []
for bang in range(number_of_frames):
spek = rfft(window(cut(audio)))
p1, p2 = speaks(spek)
if kwargs["SPECTRAL_WHITENING"]:
p2 = sw(spek, p1, p2)
pcp = hpcp(p1, p2)
if np.sum(pcp) > 0:
if not kwargs["DETUNING_CORRECTION"] or kwargs[
"DETUNING_CORRECTION_SCOPE"] == 'average':
chroma.append(pcp)
elif kwargs["DETUNING_CORRECTION"] and kwargs[
"DETUNING_CORRECTION_SCOPE"] == 'frame':
pcp = _detuning_correction(pcp, kwargs["HPCP_SIZE"])
chroma.append(pcp)
else:
raise NameError(
"SHIFT_SCOPE musts be set to 'frame' or 'average'.")
if not chroma:
return 'Silence'
chroma = np.sum(chroma, axis=0)
chroma = norm_peak(chroma)
if kwargs["PCP_THRESHOLD"] is not None:
chroma = vector_threshold(chroma, kwargs["PCP_THRESHOLD"])
if kwargs["DETUNING_CORRECTION"] and kwargs[
"DETUNING_CORRECTION_SCOPE"] == 'average':
chroma = _detuning_correction(chroma, kwargs["HPCP_SIZE"])
# Adjust to essentia's HPCP calculation starting on A (pc = 9)
chroma = np.roll(chroma, -3 * (kwargs["HPCP_SIZE"] // 12))
estimation_1 = estimate_key(chroma,
kwargs["KEY_PROFILE"],
kwargs["PROFILE_INTERPOLATION"],
conf_thres=kwargs["NOKEY_THRESHOLD"],
vocabulary=kwargs["KEY_VOCABULARY"])
key_1 = estimation_1[0]
correlation_value = estimation_1[1]
if kwargs["WITH_MODAL_DETAILS"]:
estimation_2 = _key7(chroma, kwargs["PROFILE_INTERPOLATION"])
key_2 = estimation_2[0] + '\t' + estimation_2[1]
key_verbose = key_1 + '\t' + key_2
key = key_verbose.split('\t')
# Assign monotonic track to minor:
if key[3] == 'monotonic' and key[0] == key[2]:
key = '{0}\tminor'.format(key[0])
else:
key = key_1
else:
key = key_1
textfile = open(output_text_file, 'w')
textfile.write(key)
textfile.close()
return key, correlation_value
def key_ecir(input_audio_file, output_text_file, **kwargs):
if not kwargs:
kwargs = KEY_SETTINGS
loader = estd.MonoLoader(filename=input_audio_file,
sampleRate=kwargs["SAMPLE_RATE"])
cut = estd.FrameCutter(frameSize=kwargs["WINDOW_SIZE"],
hopSize=kwargs["HOP_SIZE"])
window = estd.Windowing(size=kwargs["WINDOW_SIZE"],
type=kwargs["WINDOW_SHAPE"])
rfft = estd.Spectrum(size=kwargs["WINDOW_SIZE"])
sw = estd.SpectralWhitening(maxFrequency=kwargs["MAX_HZ"],
sampleRate=kwargs["SAMPLE_RATE"])
speaks = estd.SpectralPeaks(
magnitudeThreshold=kwargs["SPECTRAL_PEAKS_THRESHOLD"],
maxFrequency=kwargs["MAX_HZ"],
minFrequency=kwargs["MIN_HZ"],
maxPeaks=kwargs["SPECTRAL_PEAKS_MAX"],
sampleRate=kwargs["SAMPLE_RATE"])
hpcp = estd.HPCP(bandPreset=kwargs["HPCP_BAND_PRESET"],
splitFrequency=kwargs["HPCP_SPLIT_HZ"],
harmonics=kwargs["HPCP_HARMONICS"],
maxFrequency=kwargs["MAX_HZ"],
minFrequency=kwargs["MIN_HZ"],
nonLinear=kwargs["HPCP_NON_LINEAR"],
normalized=kwargs["HPCP_NORMALIZE"],
referenceFrequency=kwargs["HPCP_REFERENCE_HZ"],
sampleRate=kwargs["SAMPLE_RATE"],
size=kwargs["HPCP_SIZE"],
weightType=kwargs["HPCP_WEIGHT_TYPE"],
windowSize=kwargs["HPCP_WEIGHT_WINDOW_SEMITONES"],
maxShifted=kwargs["HPCP_SHIFT"])
key = estd.Key(numHarmonics=kwargs["KEY_HARMONICS"],
pcpSize=kwargs["HPCP_SIZE"],
profileType=kwargs["KEY_PROFILE"],
slope=kwargs["KEY_SLOPE"],
usePolyphony=kwargs["KEY_POLYPHONY"],
useThreeChords=kwargs["KEY_USE_THREE_CHORDS"])
audio = loader()
if kwargs["HIGHPASS_CUTOFF"] is not None:
hpf = estd.HighPass(cutoffFrequency=kwargs["HIGHPASS_CUTOFF"],
sampleRate=kwargs["SAMPLE_RATE"])
audio = hpf(hpf(hpf(audio)))
if kwargs["DURATION"] is not None:
audio = audio[(kwargs["START_TIME"] *
kwargs["SAMPLE_RATE"]):(kwargs["DURATION"] *
kwargs["SAMPLE_RATE"])]
duration = len(audio)
number_of_frames = int(duration / kwargs["HOP_SIZE"])
chroma = []
for bang in range(number_of_frames):
spek = rfft(window(cut(audio)))
p1, p2 = speaks(spek) # p1 = frequencies; p2 = magnitudes
if kwargs["SPECTRAL_WHITENING"]:
p2 = sw(spek, p1, p2)
vector = hpcp(p1, p2)
sum_vector = np.sum(vector)
if sum_vector > 0:
if kwargs["DETUNING_CORRECTION"] == False or kwargs[
"DETUNING_CORRECTION_SCOPE"] == 'average':
chroma.append(vector)
elif kwargs["DETUNING_CORRECTION"] and kwargs[
"DETUNING_CORRECTION_SCOPE"] == 'frame':
vector = _detuning_correction(vector, kwargs["HPCP_SIZE"])
chroma.append(vector)
else:
print("SHIFT_SCOPE must be set to 'frame' or 'average'")
chroma = np.mean(chroma, axis=0)
if kwargs["DETUNING_CORRECTION"] and kwargs[
"DETUNING_CORRECTION_SCOPE"] == 'average':
chroma = _detuning_correction(chroma, kwargs["HPCP_SIZE"])
key = key(chroma.tolist())
confidence = (key[2], key[3])
key = key[0] + '\t' + key[1]
textfile = open(output_text_file, 'w')
textfile.write(key + '\n')
textfile.close()
return key, confidence
def analysis_function(loop, sampleRate=16000):
lp_filter = es.LowPass(cutoffFrequency=90, sampleRate=sampleRate)
bp_filter = es.BandPass(bandwidth=20,
cutoffFrequency=280,
sampleRate=sampleRate)
hp_filter = es.HighPass(cutoffFrequency=9000, sampleRate=sampleRate)
[_, pattern] = ADT([loop],
output_act='yes',
tab='no',
save_dir="analysis/")
pattern = np.array(pattern)[0]
time_audio = np.linspace(0, float(29538) / 16000, 29538)
time_act = np.linspace(0, float(29538) / 16000, 160)
final_pattern = np.clip(
np.array([
interp1d(time_act, pattern[0, :, 0])(time_audio),
interp1d(time_act, pattern[1, :, 0])(time_audio),
interp1d(time_act, pattern[2, :, 0])(time_audio)
]).T, 0.0, 1.0)
final_pattern = final_pattern / final_pattern.max(axis=0)
final_pattern = np.expand_dims(final_pattern, 0)
audio_file = es.MonoLoader(filename=loop, sampleRate=sampleRate)
loop_basename = ntpath.basename(loop)
lpf_audio = lp_filter(audio_file())
bpf_audio = bp_filter(audio_file())
hpf_audio = hp_filter(audio_file())
sf.write("analysis/lpf_" + loop_basename, lpf_audio, sampleRate)
sf.write("analysis/bpf_" + loop_basename, bpf_audio, sampleRate)
sf.write("analysis/hpf_" + loop_basename, hpf_audio, sampleRate)
unordered_kick_features = timbral_models.timbral_extractor(
"analysis/lpf_" + loop_basename, clip_output=True)
unordered_snare_features = timbral_models.timbral_extractor(
"analysis/bpf_" + loop_basename, clip_output=True)
unordered_hh_features = timbral_models.timbral_extractor("analysis/hpf_" +
loop_basename,
clip_output=True)
features_kick = [
unordered_kick_features['warmth'] / 69.738235,
unordered_kick_features['roughness'] / 71.95989,
unordered_kick_features['brightness'] / 82.336105,
unordered_kick_features['hardness'] / 75.53646,
unordered_kick_features['boominess'] / 71.00043,
unordered_kick_features['depth'] / 100.0,
unordered_kick_features['sharpness'] / 81.7323,
]
features_snare = [
unordered_snare_features['warmth'] / 69.57681,
unordered_snare_features['roughness'] / 67.66642,
unordered_snare_features['brightness'] / 80.19115,
unordered_snare_features['hardness'] / 71.689445,
unordered_snare_features['boominess'] / 61.422714,
unordered_snare_features['depth'] / 100.0,
unordered_snare_features['sharpness'] / 71.406494
]
features_hh = [
unordered_hh_features['warmth'] / 32.789112,
unordered_hh_features['roughness'] / 1.0,
unordered_hh_features['brightness'] / 85.24432,
unordered_hh_features['hardness'] / 67.71172,
unordered_hh_features['boominess'] / 2.491137,
unordered_hh_features['depth'] / 0.5797179,
unordered_hh_features['sharpness'] / 87.83693
]
hpcp = file_to_hpcp(audio_file())
#[69.57681, 67.66642, 80.19115, 71.689445, 61.422714, 100.0, 71.406494]
#[32.789112, 1.0, 85.24432, 67.71172, 2.491137, 0.5797179, 87.83693]
#[69.738235, 71.95989, 82.336105, 75.53646, 71.00043, 100.0, 81.7323]
return final_pattern, hpcp, features_kick, features_snare, np.clip(
features_hh, 0, 1)