add input for reference signal in params.py

README.md

@@ -17,6 +17,8 @@ Modifiable parameters are located in params.py.
 ```
 begin = 0.0 # start reading audio file after this time in seconds.
 duration = 60 # read audio file between (begin) and (begin + duration)
+begin_ref = 0.0 # beginning of the reference signal for computing cosine distance between clusters (in seconds).
+end_ref = 0.05 # end of the reference signal for computing cosine distance between clusters (in seconds).
 BINS_PER_OCTAVE = 12*3 # number of bins per octave, a multiple of 12 is suitable
 N_OCTAVES = 7 # number of considered octaves
 NFFT = 2**11 # number of points of the analysis window, a multiple of 2 is suitable (> 2**6)
@@ -60,7 +62,7 @@ Usage:
 python3 TF_differential.py audio/filename.wav
 ```
 
-From an original idea of Jean-Marc Chouvel (http://www.ems-network.org/spip.php?article294).
+From an original idea of Jean-Marc Chouvel [L'analyse musicale différentielle](http://www.ems-network.org/IMG/JMChouvelEMS07/index.html).
 
 ### Bibliography
 * B. McFee and D P.W. Ellis (2014). Analyzing song structure with spectral clustering. In proc. of International Society for Music Information Retrieval.

params.py

 #general load WAV
 begin = 0.0 #start reading the analysed signal after this time (in seconds)
 duration = 60*2 # duration of the analysed signal (in seconds).
+begin_ref = 0.0 #beginning of the reference signal for computing cosine distance between clusters (in seconds).
+end_ref = 0.05 #end of the reference signal for computing cosine distance between clusters (in seconds).
 BINS_PER_OCTAVE = 12 * 3
 N_OCTAVES = 7
 NFFT = 2 ** 11 #(> 2**10) duration of analysis window in samples for feature extraction only.
@@ -26,8 +28,8 @@ cluster_dist = True # add cosine distance between clusters on final plot
 cluster_nb_max = 5 #maximum nb of clusters in 1 sec.
 
 #plots
-plot_simi = False
-plot_struct = False
-plot_dist = False
+plot_simi = True
+plot_struct = True
+plot_dist = True
 plot_features = True
 timestamps = True

spectral_clustering_audio.py

@@ -564,6 +564,12 @@ def extract_distance_between_clusters(center_clusters, type_dist = 'cos'):
 	
 	return distance
 	
+	
+
+def extract_ref_signal(X, onset_times):
+	ind = np.where((onset_times >= params.begin_ref) & (onset_times < params.end_ref))
+	return X[ind,:]
+
 
 
 def main():
@@ -585,7 +591,6 @@ def main():
 	
 	#extract acoustic feature from audio signal feat is a matrix np.array((nb features, Tmax*sr/STEP))
 	feat = feature_extraction(y, sr, params.opt_tuning)
-	
 
 	#extract onset indexes and times + onset-synchronous CQT transform on onsets.
 	onsets, onset_times, Csync = extract_onsets(y, sr, args.manual_onset)
@@ -651,6 +656,7 @@ def main():
 		#if needed compute the cosine distance between each cluster and a reference taken at the very begining of th signal
 		#KM.cluster_centers_ : array, [n_clusters, n_features]
 		if params.cluster_dist:
+			ref_signal = extract_ref_signal(X, onset_times)
 			distance_cosine_cluster = extract_cosine_distance_clusters( KM.cluster_centers_, np.mean(X[:10*NFFT,:], axis=0))
 		else:
 			distance_cosine_cluster = None