Picture for Xiao-Lei Zhang

Xiao-Lei Zhang

Rethinking the Output Architecture for Sound Source Localization

Add code
Nov 21, 2023
Viaarxiv icon

Diffusion-Based Adversarial Purification for Speaker Verification

Oct 24, 2023
Viaarxiv icon

Spatial-temporal Graph Based Multi-channel Speaker Verification With Ad-hoc Microphone Arrays

Add code
Jul 03, 2023
Figure 1 for Spatial-temporal Graph Based Multi-channel Speaker Verification With Ad-hoc Microphone Arrays
Figure 2 for Spatial-temporal Graph Based Multi-channel Speaker Verification With Ad-hoc Microphone Arrays
Figure 3 for Spatial-temporal Graph Based Multi-channel Speaker Verification With Ad-hoc Microphone Arrays
Figure 4 for Spatial-temporal Graph Based Multi-channel Speaker Verification With Ad-hoc Microphone Arrays
Viaarxiv icon

Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays

Apr 15, 2023
Figure 1 for Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays
Figure 2 for Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays
Figure 3 for Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays
Figure 4 for Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays
Viaarxiv icon

Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent

Feb 27, 2023
Figure 1 for Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent
Figure 2 for Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent
Figure 3 for Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent
Figure 4 for Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent
Viaarxiv icon

Interpretable Spectrum Transformation Attacks to Speaker Recognition

Feb 21, 2023
Figure 1 for Interpretable Spectrum Transformation Attacks to Speaker Recognition
Figure 2 for Interpretable Spectrum Transformation Attacks to Speaker Recognition
Figure 3 for Interpretable Spectrum Transformation Attacks to Speaker Recognition
Figure 4 for Interpretable Spectrum Transformation Attacks to Speaker Recognition
Viaarxiv icon

LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification

Add code
Nov 02, 2022
Figure 1 for LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification
Figure 2 for LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification
Figure 3 for LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification
Figure 4 for LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification
Viaarxiv icon

Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames

Add code
Nov 02, 2022
Viaarxiv icon

Symmetric Saliency-based Adversarial Attack To Speaker Identification

Add code
Oct 30, 2022
Figure 1 for Symmetric Saliency-based Adversarial Attack To Speaker Identification
Figure 2 for Symmetric Saliency-based Adversarial Attack To Speaker Identification
Figure 3 for Symmetric Saliency-based Adversarial Attack To Speaker Identification
Figure 4 for Symmetric Saliency-based Adversarial Attack To Speaker Identification
Viaarxiv icon

WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit

Add code
Oct 30, 2022
Figure 1 for WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit
Figure 2 for WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit
Figure 3 for WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit
Figure 4 for WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit
Viaarxiv icon