Area of research
Signal Processing · Artificial Intelligence
Research interest
Research interests include Computer science, Speech recognition, Speaker verification, Artificial intelligence, Embedding, and Robustness (evolution).
PROSE: Probabilistic Reinforcement Learning Optimized by Success Estimation for Stage-Aware Cotton Irrigation Scheduling
Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection
Dual-Path Spectrogram Refinement Network for Robust Speaker Verification
Improving Speaker Verification Back-End with Graph Neural Networks
Anomalous Sound Detection Using Time-Frequency Feature and Mixbatch
Alignment Losses for End-to-End Speaker Diarization
AGDAformer: Agent-Guidance Dual Attention Transformer for Climate-Aware Crop Yield Prediction
Multi-level Adversarial Training with Data Augmentation for Robust Speaker Verification
Improving Speaker Verification With Noise-Aware Label Ensembling and Sample Selection: Learning and Correcting Noisy Speaker Labels
Multi-View Speaker Embedding Learning for Enhanced Stability and Discriminability
LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Verification
Branch-Transformer: A Parallel Branch Architecture to Capture Local and Global Features for Language Identification
Simplified Skip-Connected UNet for Robust Speaker Verification Under Noisy Environments
Pseudo-Phoneme Label Loss for Text-Independent Speaker Verification
Virtual Fully-Connected Layer for a Large-Scale Speaker Verification Dataset