Speech Separation
Speech separation refers to the task of extracting all overlapping speech sources from a mixed speech signal. As a specific scenario of source separation problems, speech separation primarily focuses on isolating multiple simultaneously occurring speech signals rather than other interfering signals such as music or noise. This technology holds significant application value in speech recognition in multi-speaker environments, hearing assistance devices, and audio editing.
GRID corpus (mixed-speech)
iKala
U-Net
Libri10Mix
Libri15Mix
Hungarian PIT
Libri20Mix
Libri2Mix
MossFormer2 (w speed perturb)
Libri5Mix
Hungarian PIT
LibriCSS
Conformer (large)
LRS2
TDFNet-small
LRS3
IIANet
TCD-TIMIT corpus (mixed-speech)
VoxCeleb2
RTFS-Net-4
WHAM!
SepReformer-L + DM
WHAMR!
TF-Locoformer (M)
WSJ0-2mix
SepReformer-L
WSJ0-2mix-16k
MossFormer2
WSJ0-3mix
Gated DualPathRNN
WSJ0-4mix
WSJ0-5mix
Gated DualPathRNN