Zhengyang Chen

Latest

• Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition
• Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor
• Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit
• DF-ResNet: Boosting Speaker Verification Performance with Depth-First Design
• Self-Knowledge Distillation via Feature Enhancement for Speaker Verification
• Speaker Embedding Augmentation with Noise Distribution Matching.
• SELF-SUPERVISED LEARNING BASED DOMAIN ADAPTATION FOR ROBUST SPEAKER VERIFICATION
• Audio-Visual Deep Neural Network for Robust Person Verification
• Multi-modality Matters: A Performance Leap on VoxCeleb
• Adversarial Domain Adaptation for Speaker Verification using Partially Shared Network
• Channel Invariant Speaker Embedding Learning with Joint Multi-Task and Adversarial Training
• The SJTU Robust Anti-Spoofing System for the ASVspoof 2019 Challenge