Picture for Xiaohuai Le

Xiaohuai Le

Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model

Add code
Jun 01, 2023
Viaarxiv icon

Personalized speech enhancement combining band-split RNN and speaker attentive module

Add code
Feb 20, 2023
Viaarxiv icon

Inference skipping for more efficient real-time speech enhancement with parallel RNNs

Add code
Jul 22, 2022
Figure 1 for Inference skipping for more efficient real-time speech enhancement with parallel RNNs
Figure 2 for Inference skipping for more efficient real-time speech enhancement with parallel RNNs
Figure 3 for Inference skipping for more efficient real-time speech enhancement with parallel RNNs
Figure 4 for Inference skipping for more efficient real-time speech enhancement with parallel RNNs
Viaarxiv icon

A light-weight full-band speech enhancement model

Add code
Jul 03, 2022
Figure 1 for A light-weight full-band speech enhancement model
Figure 2 for A light-weight full-band speech enhancement model
Figure 3 for A light-weight full-band speech enhancement model
Viaarxiv icon

DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

Add code
Jul 12, 2021
Figure 1 for DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement
Figure 2 for DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement
Figure 3 for DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement
Viaarxiv icon