From: Dynamically localizing multiple speakers based on the time-frequency domain
Test room
Room 1
Room 2
Measure
MAE
Acc.
MUSIC [2]
27.95
28.34
31.62
18.38
SRP-PHAT [3]
28.25
27.23
36.61
36.28
CMS-DOA [5]
12.87
73.09
24.0
39.25
TF-DOAnet (our algorithm)
1.58
97.45
2.76
93.0
