Picture for Xihong Wu

Xihong Wu

Using Ear-EEG to Decode Auditory Attention in Multiple-speaker Environment

Add code
Sep 13, 2024
Viaarxiv icon

DENSE: Dynamic Embedding Causal Target Speech Extraction

Add code
Sep 10, 2024
Viaarxiv icon

Cross-attention Inspired Selective State Space Models for Target Sound Extraction

Add code
Sep 10, 2024
Figure 1 for Cross-attention Inspired Selective State Space Models for Target Sound Extraction
Figure 2 for Cross-attention Inspired Selective State Space Models for Target Sound Extraction
Figure 3 for Cross-attention Inspired Selective State Space Models for Target Sound Extraction
Figure 4 for Cross-attention Inspired Selective State Space Models for Target Sound Extraction
Viaarxiv icon

Leveraging Moving Sound Source Trajectories for Universal Sound Separation

Add code
Sep 07, 2024
Figure 1 for Leveraging Moving Sound Source Trajectories for Universal Sound Separation
Figure 2 for Leveraging Moving Sound Source Trajectories for Universal Sound Separation
Figure 3 for Leveraging Moving Sound Source Trajectories for Universal Sound Separation
Figure 4 for Leveraging Moving Sound Source Trajectories for Universal Sound Separation
Viaarxiv icon

TSE-PI: Target Sound Extraction under Reverberant Environments with Pitch Information

Add code
Jun 13, 2024
Viaarxiv icon

Beware of Overestimated Decoding Performance Arising from Temporal Autocorrelations in Electroencephalogram Signals

Add code
May 27, 2024
Figure 1 for Beware of Overestimated Decoding Performance Arising from Temporal Autocorrelations in Electroencephalogram Signals
Figure 2 for Beware of Overestimated Decoding Performance Arising from Temporal Autocorrelations in Electroencephalogram Signals
Figure 3 for Beware of Overestimated Decoding Performance Arising from Temporal Autocorrelations in Electroencephalogram Signals
Figure 4 for Beware of Overestimated Decoding Performance Arising from Temporal Autocorrelations in Electroencephalogram Signals
Viaarxiv icon

Self-supervised speech representation and contextual text embedding for match-mismatch classification with EEG recording

Add code
Feb 01, 2024
Viaarxiv icon

ConvConcatNet: a deep convolutional neural network to reconstruct mel spectrogram from the EEG

Add code
Jan 10, 2024
Viaarxiv icon

A DenseNet-based method for decoding auditory spatial attention with EEG

Add code
Sep 14, 2023
Viaarxiv icon

Semantic reconstruction of continuous language from MEG signals

Add code
Sep 14, 2023
Viaarxiv icon