Picture for Changchun Bao

Changchun Bao

SS-BRPE: Self-Supervised Blind Room Parameter Estimation Using Attention Mechanisms

Add code
Sep 08, 2024
Viaarxiv icon

Target Speaker Extraction by Directly Exploiting Contextual Information in the Time-Frequency Domain

Add code
Feb 27, 2024
Viaarxiv icon

Exploring the Power of Pure Attention Mechanisms in Blind Room Parameter Estimation

Add code
Feb 25, 2024
Viaarxiv icon

Attention Is All You Need For Blind Room Volume Estimation

Add code
Sep 23, 2023
Viaarxiv icon

An Effective Dereverberation Algorithm by Fusing MVDR and MCLP

Add code
Mar 28, 2022
Figure 1 for An Effective Dereverberation Algorithm by Fusing MVDR and MCLP
Figure 2 for An Effective Dereverberation Algorithm by Fusing MVDR and MCLP
Figure 3 for An Effective Dereverberation Algorithm by Fusing MVDR and MCLP
Figure 4 for An Effective Dereverberation Algorithm by Fusing MVDR and MCLP
Viaarxiv icon

Multi-source wideband doa estimation method by frequency focusing and error weighting

Add code
Mar 28, 2022
Figure 1 for Multi-source wideband doa estimation method by frequency focusing and error weighting
Figure 2 for Multi-source wideband doa estimation method by frequency focusing and error weighting
Figure 3 for Multi-source wideband doa estimation method by frequency focusing and error weighting
Figure 4 for Multi-source wideband doa estimation method by frequency focusing and error weighting
Viaarxiv icon

A Neural Vocoder Based Packet Loss Concealment Algorithm

Add code
Mar 26, 2022
Figure 1 for A Neural Vocoder Based Packet Loss Concealment Algorithm
Figure 2 for A Neural Vocoder Based Packet Loss Concealment Algorithm
Figure 3 for A Neural Vocoder Based Packet Loss Concealment Algorithm
Figure 4 for A Neural Vocoder Based Packet Loss Concealment Algorithm
Viaarxiv icon

Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation

Add code
Mar 25, 2022
Figure 1 for Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation
Figure 2 for Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation
Figure 3 for Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation
Figure 4 for Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation
Viaarxiv icon