Using information theoretic distance measures for solving the permutation problem of blind source separation of speech signals

EURASIP Journal on Audio, Speech, and Music Processing

Table 5 Average values of the obtained results of Algorithm 1 in terms of Δ SIR and SDR for each distance measure

Distance measure	ΔSIR			SDR
	M ₂	M ₃	M ₄	M ₂	M ₃	M ₄
Bhattacharyya coefficient	0.97	1.32	2.5	3.21	2.77	1.78
Kullback-Leibler divergence	0.86	2.12	1.93	5.03	3.01	1.02
Log of the maximum ratio	0.62	2.14	1.22	4.63	2.76	0.82
Jensen-Rényi divergence, α = 0.5	3.00	3.65	5.44	5.33	3.17	1.43
Jensen-Rényi divergence, α = 1	4.00	4.50	6.44	6.08	3.49	2.15
Jensen-Rényi divergence, α = 2	4.01	3.94	6.09	5.75	3.29	1.45
Mod. Jensen-Rényi divergence, α = 0.5	7.89	7.27	8.99	8.12	4.86	2.78
Mod. Jensen-Rényi divergence, α = 1	7.89	7.27	8.97	8.12	4.87	2.74
Mod. Jensen-Rényi divergence, α = 2	7.89	7.28	8.98	8.12	4.87	2.78
Mutual information	7.35	7.66	8.15	7.79	5.23	2.59

M_i stands for the average Δ SIR/SDR value calculated over all mixtures of N = i signals (cf. Tables 1, 2, 3, and 4). The best performance for each case M_i is marked in bold.