Picture for Song Li

Song Li

Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter

Add code
Sep 19, 2023
Figure 1 for Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Figure 2 for Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Figure 3 for Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Figure 4 for Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Viaarxiv icon

Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation

Apr 12, 2023
Figure 1 for Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation
Figure 2 for Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation
Figure 3 for Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation
Figure 4 for Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation
Viaarxiv icon

Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks

Add code
Nov 22, 2022
Figure 1 for Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks
Figure 2 for Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks
Figure 3 for Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks
Figure 4 for Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks
Viaarxiv icon

A Review of Intelligent Music Generation Systems

Add code
Nov 22, 2022
Figure 1 for A Review of Intelligent Music Generation Systems
Figure 2 for A Review of Intelligent Music Generation Systems
Figure 3 for A Review of Intelligent Music Generation Systems
Figure 4 for A Review of Intelligent Music Generation Systems
Viaarxiv icon

Spatial-aware Speaker Diarization for Multi-channel Multi-party Meeting

Sep 24, 2022
Figure 1 for Spatial-aware Speaker Diarization for Multi-channel Multi-party Meeting
Figure 2 for Spatial-aware Speaker Diarization for Multi-channel Multi-party Meeting
Figure 3 for Spatial-aware Speaker Diarization for Multi-channel Multi-party Meeting
Figure 4 for Spatial-aware Speaker Diarization for Multi-channel Multi-party Meeting
Viaarxiv icon

A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases

Jul 23, 2022
Figure 1 for A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases
Figure 2 for A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases
Figure 3 for A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases
Figure 4 for A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases
Viaarxiv icon

An Interpretable Federated Learning-based Network Intrusion Detection Framework

Jan 10, 2022
Figure 1 for An Interpretable Federated Learning-based Network Intrusion Detection Framework
Figure 2 for An Interpretable Federated Learning-based Network Intrusion Detection Framework
Figure 3 for An Interpretable Federated Learning-based Network Intrusion Detection Framework
Figure 4 for An Interpretable Federated Learning-based Network Intrusion Detection Framework
Viaarxiv icon

Dynamic Differential-Privacy Preserving SGD

Add code
Nov 15, 2021
Figure 1 for Dynamic Differential-Privacy Preserving SGD
Figure 2 for Dynamic Differential-Privacy Preserving SGD
Figure 3 for Dynamic Differential-Privacy Preserving SGD
Figure 4 for Dynamic Differential-Privacy Preserving SGD
Viaarxiv icon

An Integrated Framework for Two-pass Personalized Voice Trigger

Add code
Jun 30, 2021
Figure 1 for An Integrated Framework for Two-pass Personalized Voice Trigger
Figure 2 for An Integrated Framework for Two-pass Personalized Voice Trigger
Figure 3 for An Integrated Framework for Two-pass Personalized Voice Trigger
Figure 4 for An Integrated Framework for Two-pass Personalized Voice Trigger
Viaarxiv icon

Crop Height and Plot Estimation from Unmanned Aerial Vehicles using 3D LiDAR

Add code
Oct 30, 2019
Figure 1 for Crop Height and Plot Estimation from Unmanned Aerial Vehicles using 3D LiDAR
Figure 2 for Crop Height and Plot Estimation from Unmanned Aerial Vehicles using 3D LiDAR
Figure 3 for Crop Height and Plot Estimation from Unmanned Aerial Vehicles using 3D LiDAR
Figure 4 for Crop Height and Plot Estimation from Unmanned Aerial Vehicles using 3D LiDAR
Viaarxiv icon