Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 9 Results on WHAM! and WHAMR!. Best values are marked with bold font

From: Time-domain adaptive attention network for single-channel speech separation

Model

WHAM

WHAMR

SI-SNRi

SDRi

SI-SNRi

SDRi

Chimera++ [57]

9.9

-

-

-

Conv-TasNet [49, 58]

12.7

-

8.3

-

Leamable fbank [58]

12.9

-

-

-

DPRNN [55]

13.9

-

10.3

-

SVOICE [55]

15.2

-

12.2

-

Wavesplit [21]

15.4

15.8

12.0

11.1

TAANet

15.5

15.8

12.0

11.2

Back to article page