FSformer: Sparsely and Effectively Learning Key Features for Multi-channel Speech Enhancement

Result Display

Case 1
Reverberation+Noise (Ch. 0)	Clean (Ch. 0)
SpatialNet	FSformer

Case 2
Reverberation+Noise (Ch. 0)	Clean (Ch. 0)
SpatialNet	FSformer

Case 3
Reverberation+Noise (Ch. 0)	Clean (Ch. 0)
SpatialNet	FSformer

Case 4
Reverberation+Noise (Ch. 0)	Clean (Ch. 0)
SpatialNet	FSformer

Real-case 1
Real Recording (Ch. 0)	DeFT-AN
SpatialNet	FSformer

Real-case 2
Real Recording (Ch. 0)	DeFT-AN
SpatialNet	FSformer