HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Speech Separation On Whamr

Metrics

SI-SDRi

Results

Performance results of various models on this benchmark

Paper Title
TF-Locoformer (M)18.5TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
TF-Locoformer (S)17.4TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
SepReformer-L + DM17.1Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
MossFormer217.0MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
MossFormer (L) + DM16.3MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
TD-Conformer (XL) + DM14.6On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
Improved Sudo rm -rf (U=36)13.5Compute and memory efficient universal sound source separation
TD-Conformer (L) + DM13.4On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
Wavesplit13.2Wavesplit: End-to-End Speech Separation by Speaker Clustering
DPTNET - SRSSN12.3Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
DPRNN - SRSSN12.3Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
VSUNOS12.2Voice Separation with an Unknown Number of Multiple Speakers
Sudo rm -rf (U=16)12.1Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
TD-Confomer (M) + DM12On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
Deformable TCN + Dynamic Mixing11.1Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
TD-Confomer (S)10.5On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
Deformable TCN + Shared Weights + Dynamic Mixing10.1Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
Bi-LSTM-TASNET9.2WHAM!: Extending Speech Separation to Noisy Environments
0 of 18 row(s) selected.