def chroma_cqt(y=None, sr=22050, C=None, hop_length=512, fmin=None,
norm=np.inf, threshold=0.0, tuning=None, n_chroma=12,
n_octaves=7, window=None, bins_per_octave=None, cqt_mode='full'):
cqt_func = {'full': cqt, 'hybrid': hybrid_cqt}
if bins_per_octave is None:
bins_per_octave = n_chroma
# Build the CQT if we don't have one already
if C is None:
C = np.abs(cqt_func[cqt_mode](y, sr=sr,
hop_length=hop_length,
fmin=fmin,
n_bins=n_octaves * bins_per_octave,
bins_per_octave=bins_per_octave,
tuning=tuning))
# Map to chroma
cq_to_chr = filters.cq_to_chroma(C.shape[0],
bins_per_octave=bins_per_octave,
n_chroma=n_chroma,
fmin=fmin,
window=window)
chroma = cq_to_chr.dot(C)
if threshold is not None:
chroma[chroma < threshold] = 0.0
# Normalize
if norm is not None:
chroma = util.normalize(chroma, norm=norm, axis=0)
return chroma
def fingerprint_chromagram(audio_signal, audio_parameters):
# Parameter(s)
sample_rate = audio_parameters['sample_rate']
time_resolution = audio_parameters['time_resolution']
cqt_kernel = audio_parameters['cqt_kernel']
neighborhood_size = audio_parameters['neighborhood_size']
frequency_resolution = audio_parameters['frequency_resolution']
bins_per_octave = 24 * frequency_resolution
minimum_frequency = audio_parameters['minimum_frequency']
# Transform the signal into a log-scaled spectrogram using the CQT
audio_spectrogram = spectrogram(audio_signal, sample_rate, time_resolution,
cqt_kernel)
# Convert the spectrogram to uint8 (to speed up medfilt2) (in Matlab!)
audio_spectrogram = np.uint8(
np.around(255 * audio_spectrogram / np.amax(audio_spectrogram)))
audio_fingerprint = (audio_spectrogram > ndimage.median_filter(
audio_spectrogram, neighborhood_size, mode='reflect')).astype(float)
chroma_filter = cq_to_chroma(audio_fingerprint.shape[0],
bins_per_octave=bins_per_octave,
fmin=minimum_frequency)
chromagram = chroma_filter.dot(audio_fingerprint)
return chromagram
def GetChromaFromPianoroll(arr_pianoroll,bass=False):
chroma_filter = cq_to_chroma(n_input=128,fmin=midi_to_hz(0))
chroma = np.dot(chroma_filter,arr_pianoroll.T).T.astype("float32")
chroma[chroma>0] = 1
if not bass:
return chroma
bass_chroma = np.zeros(shape=chroma.shape,dtype="float32")
for t in range(bass_chroma.shape[0]):
notes = arr_pianoroll[t,:]
if np.sum(notes)>0:
bass = np.min(np.where(notes>0)[0])
bass_chroma[i,bass%12] = 1
return np.concatenate([bass_chroma,chroma],axis=1)
def GetLabelarrFromPianoroll(arr_pianoroll):
chroma_filter = cq_to_chroma(n_input = 128, fmin = midi_to_hz(0)).T
chroma = np.dot(arr_pianoroll,chroma_filter).astype("int32")
lab = np.zeros(chroma.shape[0],dtype="int32")
for i in range(chroma.shape[0]):
c = chroma[i,:]
note = arr_pianoroll[i,:]
bass = np.where(note>0)[0]
if bass.size>0:
c[np.min(bass)%12] = 20 #Force bass note to remain in template
c_argsort = np.argsort(c,kind="mergesort")
c[c_argsort[:9]] = 0
lab[i] = _getlabel(c)
return lab
def GetTemplateChromaFromPianoroll(arr_pianoroll,bass=False):
chroma_filter = cq_to_chroma(n_input = 128, fmin = midi_to_hz(0)).T
chroma = np.dot(arr_pianoroll,chroma_filter).astype("int32")
chroma_template = np.zeros(chroma.shape,dtype="int32")
bass_template = np.zeros(chroma.shape,dtype="int32")
for i in range(chroma.shape[0]):
c = chroma[i,:]
note = arr_pianoroll[i,:]
bass = np.where(note>0)[0]
if bass.size>0:
if not bass:
c[np.min(bass)%12] = 20 #Force bass note to remain in template
bass_template[i,np.min(bass)] = 1
c_argsort = np.argsort(c,kind="mergesort")
c[c_argsort[:9]] = 0
c[c>0] = 1
chroma_template[i,:] = c
if bass:
return np.concatenate([chroma_template,bass_template],axis=1)
else:
return chroma_template
def GetTargetsFromPianoroll(arr_pianoroll):
chroma_filter = cq_to_chroma(n_input=128,fmin=midi_to_hz(0))
T = arr_pianoroll.shape[0]
t_bass = np.zeros(T,dtype="int32")
t_top = np.zeros(T,dtype="int32")
for t in range(T):
sum_notes = np.sum(arr_pianoroll[t,:])
if sum_notes==0:
continue
notes = np.where(arr_pianoroll[t,:]>0)[0]
bassnote = np.min(notes)
topnote = np.max(notes)
arr_pianoroll[t,bassnote]=0
arr_pianoroll[t,topnote]=0
t_bass[t]=bassnote%12
t_top[t]=topnote%12
chroma = np.dot(chroma_filter,arr_pianoroll.T).T.astype("float32")
feature = np.zeros((T,12),dtype="float32")
feature[chroma>=1] = 1.0
return t_bass,feature,t_top
def GetConvnetTargetFromPianoroll(arr_pianoroll):
chroma_filter = cq_to_chroma(n_input=128,fmin=midi_to_hz(0))
T = arr_pianoroll.shape[0]
bass_chroma = np.zeros((T,12),dtype="float32")
top_chroma = np.zeros((T,12),dtype="float32")
for t in range(T):
sum_notes = np.sum(arr_pianoroll[t,:])
if sum_notes==0:
continue
notes = np.where(arr_pianoroll[t,:]>0)[0]
bassnote = np.min(notes)
topnote = np.max(notes)
arr_pianoroll[t,bassnote]=0
arr_pianoroll[t,topnote]=0
bass_chroma[t,bassnote%12]=1
top_chroma[t,topnote%12]=1
chroma = np.dot(chroma_filter,arr_pianoroll.T).T
feature = np.zeros((T,12),dtype="float32")
#feature = normalize(chroma,axis=1,norm=np.inf).astype("float32")
feature[chroma>=1] = 1.0
feature = np.concatenate([bass_chroma,feature,top_chroma],axis=1)
return feature
temp_C = np.array([[1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0],
[1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0],
[1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0],
[1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0],
[1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0],
[1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0],
[1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0],
[1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1]])
qualities = ["", "min", "dim", "dim", "aug", "7", "min7", "maj7"]
notes = ["C", "C#", "D", "D#", "E", "F", "F#", "G", "G#", "A", "A#", "B"]
mat_templates = np.zeros((12 * len(qualities), 12))
chromafilter = cq_to_chroma(88)
for q in range(len(qualities)):
for r in range(12):
mat_templates[12 * q + r, :] = np.roll(temp_C[q, :], r)
def match_chord(segment, thld=0.2):
"""
Compare the segment note information with chord templates
"""
bassnote = np.min(np.nonzero(segment > (segment.max() * thld))[0])
bassnote_chroma = bassnote % 12
n_notes = segment.size
chroma = np.dot(chromafilter[:, :n_notes], segment[:, None])
chroma /= chroma.max()