### Initializations
pt_dir = 'Examples/Pitch Tracks/'
pd_dir = 'Examples/PD/'
pcd_dir = 'Examples/PCD/'
b = be.BozkurtEstimation()
###---------------------------------------------------------------------------------------
### Loading the pitch tracks
pt1 = mf.load_track('semahat', pt_dir)[:, 1]
###---------------------------------------------------------------------------------------
### Loading the existing pitch distributions. The JSON related issues are handled
### internally, no need to import json.
pcd1 = p_d.load('semahat_pcd.json', pcd_dir)
pcd2 = p_d.load('gec_kalma_pcd.json', pcd_dir)
pcd3 = p_d.load('murat_derya_pcd.json', pcd_dir)
### You don't need to worry about KDE, if you just want to use the function as it is. KDE
### returns the Kernel Density Estimation, in case you might use in another analysis.
pd = p_d.load('gec_kalma_pd.json', pd_dir)
### They can plotted like this.
#pcd1.plot() # This is Figure 1
#pd.plot() # This is Figure 2
###---------------------------------------------------------------------------------------
### Here comes the actual training part. After the following lines, the joint distributions
### of the modes should be saved in your working directory.
ussak_pcd = b.train('ussak_pcd', [(pt_dir + 'semahat'), (pt_dir + 'gec_kalma'),
def estimate(self, pitch_track, mode_names=[], mode_name='', mode_dir='./', est_tonic=True, est_mode=True, rank=1, distance_method="euclidean", metric='pcd', ref_freq=440): """--------------------------------------------------------------------------------------- This is the high level function that users are expected to interact with, for estimation purposes. Using the est_* flags, it is possible to estimate tonic, mode or both. ---------------------------------------------------------------------------------------""" ### Preliminaries before the estimations cent_track = mf.hz_to_cent(pitch_track, ref_freq=ref_freq) dist = mf.generate_pd(cent_track, ref_freq=ref_freq, smooth_factor=self.smooth_factor, cent_ss=self.cent_ss) dist = mf.generate_pcd(dist) if (metric=='pcd') else dist mode_dists = [(p_d.load((m + '_' + metric + '.json'), mode_dir)) for m in mode_names] mode_dist = p_d.load((mode_name + '_' + metric + '.json'), mode_dir) if (mode_name!='') else None tonic_list = np.zeros(rank) mode_list = ['' for x in range(rank)] if(est_tonic): if(metric=='pcd'): ### Shifting to the global minima to prevent wrong detection of peaks shift_factor = dist.vals.tolist().index(min(dist.vals)) dist = dist.shift(shift_factor) anti_freq = mf.cent_to_hz([dist.bins[shift_factor]], ref_freq=ref_freq)[0] peak_idxs, peak_vals = dist.detect_peaks() elif(metric=='pd'): peak_idxs, peak_vals = dist.detect_peaks() origin = np.where(dist.bins==0)[0][0] shift_idxs = [(idx - origin) for idx in peak_idxs] ### Call to actual estimation functions if(est_tonic and est_mode): if(metric=='pcd'): dist_mat = mf.generate_distance_matrix(dist, peak_idxs, mode_dists, method=distance_method) for r in range(rank): min_row = np.where((dist_mat == np.amin(dist_mat)))[0][0] min_col = np.where((dist_mat == np.amin(dist_mat)))[1][0] tonic_list[r] = mf.cent_to_hz([dist.bins[peak_idxs[min_row]]], anti_freq)[0] mode_list[r] = mode_names[min_col] dist_mat[min_row][min_col] = (np.amax(dist_mat) + 1) return mode_list, tonic_list elif(metric=='pd'): dist_mat = np.zeros((len(shift_idxs), len(mode_dists))) for m in range(len(mode_dists)): dist_mat[:,m] = self.tonic_estimate(dist, shift_idxs, mode_dists[m], distance_method=distance_method, metric=metric) for r in range(rank): min_row = np.where((dist_mat == np.amin(dist_mat)))[0][0] min_col = np.where((dist_mat == np.amin(dist_mat)))[1][0] tonic_list[r] = mf.cent_to_hz([shift_idxs[min_row] * self.cent_ss], ref_freq)[0] mode_list[r] = mode_names[min_col] dist_mat[min_row][min_col] = (np.amax(dist_mat) + 1) return mode_list, tonic_list elif(est_tonic): if(metric=='pcd'): distance_vector = self.tonic_estimate(dist, peak_idxs, mode_dist, distance_method=distance_method, metric=metric) for r in range(rank): idx = np.argmin(distance_vector) tonic_list[r] = mf.cent_to_hz([dist.bins[peak_idxs[idx]]], anti_freq)[0] distance_vector[idx] = (np.amax(distance_vector) + 1) return tonic_list elif(metric=='pd'): distance_vector = self.tonic_estimate(dist, shift_idxs, mode_dist, distance_method=distance_method, metric=metric) for r in range(rank): idx = np.argmin(distance_vector) tonic_list[r] = mf.cent_to_hz([shift_idxs[idx] * self.cent_ss], ref_freq)[0] distance_vector[idx] = (np.amax(distance_vector) + 1) return tonic_list elif(est_mode): distance_vector = self.mode_estimate(dist, mode_dists, distance_method=distance_method, metric=metric) for r in range(rank): idx = np.argmin(distance_vector) mode_list[r] = mode_names[idx] distance_vector[idx] = (np.amax(distance_vector) + 1) return mode_list else: # Nothing is expected to be estimated return 0
def estimate(self,
pitch_track,
mode_names=[],
mode_name='',
mode_dir='./',
est_tonic=True,
est_mode=True,
rank=1,
distance_method="euclidean",
metric='pcd',
ref_freq=440):
"""---------------------------------------------------------------------------------------
This is the high level function that users are expected to interact with, for estimation
purposes. Using the est_* flags, it is possible to estimate tonic, mode or both.
---------------------------------------------------------------------------------------"""
### Preliminaries before the estimations
cent_track = mf.hz_to_cent(pitch_track, ref_freq=ref_freq)
dist = mf.generate_pd(cent_track,
ref_freq=ref_freq,
smooth_factor=self.smooth_factor,
cent_ss=self.cent_ss)
dist = mf.generate_pcd(dist) if (metric == 'pcd') else dist
mode_dists = [(p_d.load((m + '_' + metric + '.json'), mode_dir))
for m in mode_names]
mode_dist = p_d.load(
(mode_name + '_' + metric +
'.json'), mode_dir) if (mode_name != '') else None
tonic_list = np.zeros(rank)
mode_list = ['' for x in range(rank)]
if (est_tonic):
if (metric == 'pcd'):
### Shifting to the global minima to prevent wrong detection of peaks
shift_factor = dist.vals.tolist().index(min(dist.vals))
dist = dist.shift(shift_factor)
anti_freq = mf.cent_to_hz([dist.bins[shift_factor]],
ref_freq=ref_freq)[0]
peak_idxs, peak_vals = dist.detect_peaks()
elif (metric == 'pd'):
peak_idxs, peak_vals = dist.detect_peaks()
origin = np.where(dist.bins == 0)[0][0]
shift_idxs = [(idx - origin) for idx in peak_idxs]
### Call to actual estimation functions
if (est_tonic and est_mode):
if (metric == 'pcd'):
dist_mat = mf.generate_distance_matrix(dist,
peak_idxs,
mode_dists,
method=distance_method)
for r in range(rank):
min_row = np.where((dist_mat == np.amin(dist_mat)))[0][0]
min_col = np.where((dist_mat == np.amin(dist_mat)))[1][0]
tonic_list[r] = mf.cent_to_hz(
[dist.bins[peak_idxs[min_row]]], anti_freq)[0]
mode_list[r] = mode_names[min_col]
dist_mat[min_row][min_col] = (np.amax(dist_mat) + 1)
return mode_list, tonic_list
elif (metric == 'pd'):
dist_mat = np.zeros((len(shift_idxs), len(mode_dists)))
for m in range(len(mode_dists)):
dist_mat[:, m] = self.tonic_estimate(
dist,
shift_idxs,
mode_dists[m],
distance_method=distance_method,
metric=metric)
for r in range(rank):
min_row = np.where((dist_mat == np.amin(dist_mat)))[0][0]
min_col = np.where((dist_mat == np.amin(dist_mat)))[1][0]
tonic_list[r] = mf.cent_to_hz(
[shift_idxs[min_row] * self.cent_ss], ref_freq)[0]
mode_list[r] = mode_names[min_col]
dist_mat[min_row][min_col] = (np.amax(dist_mat) + 1)
return mode_list, tonic_list
elif (est_tonic):
if (metric == 'pcd'):
distance_vector = self.tonic_estimate(
dist,
peak_idxs,
mode_dist,
distance_method=distance_method,
metric=metric)
for r in range(rank):
idx = np.argmin(distance_vector)
tonic_list[r] = mf.cent_to_hz([dist.bins[peak_idxs[idx]]],
anti_freq)[0]
distance_vector[idx] = (np.amax(distance_vector) + 1)
return tonic_list
elif (metric == 'pd'):
distance_vector = self.tonic_estimate(
dist,
shift_idxs,
mode_dist,
distance_method=distance_method,
metric=metric)
for r in range(rank):
idx = np.argmin(distance_vector)
tonic_list[r] = mf.cent_to_hz(
[shift_idxs[idx] * self.cent_ss], ref_freq)[0]
distance_vector[idx] = (np.amax(distance_vector) + 1)
return tonic_list
elif (est_mode):
distance_vector = self.mode_estimate(
dist,
mode_dists,
distance_method=distance_method,
metric=metric)
for r in range(rank):
idx = np.argmin(distance_vector)
mode_list[r] = mode_names[idx]
distance_vector[idx] = (np.amax(distance_vector) + 1)
return mode_list
else:
# Nothing is expected to be estimated
return 0
pt_dir = 'Examples/Pitch Tracks/'
pd_dir = 'Examples/PD/'
pcd_dir = 'Examples/PCD/'
b = be.BozkurtEstimation()
###---------------------------------------------------------------------------------------
### Loading the pitch tracks
pt1 = mf.load_track('semahat', pt_dir)[:,1]
###---------------------------------------------------------------------------------------
### Loading the existing pitch distributions. The JSON related issues are handled
### internally, no need to import json.
pcd1 = p_d.load('semahat_pcd.json', pcd_dir)
pcd2 = p_d.load('gec_kalma_pcd.json', pcd_dir)
pcd3 = p_d.load('murat_derya_pcd.json', pcd_dir)
### You don't need to worry about KDE, if you just want to use the function as it is. KDE
### returns the Kernel Density Estimation, in case you might use in another analysis.
pd = p_d.load('gec_kalma_pd.json', pd_dir)
### They can plotted like this.
#pcd1.plot() # This is Figure 1
#pd.plot() # This is Figure 2
###---------------------------------------------------------------------------------------
### Here comes the actual training part. After the following lines, the joint distributions
### of the modes should be saved in your working directory.
ussak_pcd = b.train('ussak_pcd', [(pt_dir + 'semahat'), (pt_dir + 'gec_kalma'), (pt_dir + 'murat_derya')], [199, 396.3525, 334.9488], metric='pcd')
