EURASIP Journal on Audio, Speech, and Music Processing

Table 3 Comparison of speaker counting performance under different acoustical conditions in terms of F1 score

From: Learning-based robust speaker counting and separation with the aid of spatial coherence

T60 (ms)	360			610
SNR (dB)	30	20	10	30	20	10	Avg.
baseline 1	99.40	94.42	55.94	98.81	93.72	59.00	83.55
baseline 2	99.52	96.22	82.53	99.57	96.54	84.94	93.22
proposal 1	99.62	98.66	90.79	99.72	98.63	91.29	96.45
proposal 2	99.75	99.37	91.01	99.75	99.25	91.88	96.84

Back to article page