Spatially Selective Deep Non-linear Filters for Speaker Extraction

This website accompanies our ICASSP 2023 paper:

Kristina Tesch, Timo Gerkmann, "Spatially Selective Deep Non-linear Filters for Speaker Extraction"

Spatially selective filters for speech separation

2 Speakers

Example	Mix	Speaker	Clean	JNF (proposed)	JNF (CoS)
1		1
		2
2		1
		2
3		1
		2
4		1
		2

3 Speakers

Example	Mix	Speaker	Clean	JNF (proposed)	JNF (CoS)
1		1
		2
		3
2		1
		2
		3
3		1
		2
		3
4		1
		2
		3

5 Speakers

Example	Mix	Speaker	Clean	JNF (proposed)	JNF (CoS)
1		1
		2
		3
		4
		5
2		1
		2
		3
		4
		5
3		1
		2
		3
		4
		5
4		1
		2
		3
		4
		5