Kai Yu

Latest

• UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
• Voice activity detection in the wild: A data-driven approach using teacher-student training
• Revisiting the Statistics Pooling Layer in Deep Speaker Embedding Learning
• SYNAUG:SYNTHESIS-BASED DATA AUGMENTATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION
• Data Augmentation using Deep Generative Models for Embedding based Speaker Recognition
• Text Adaptation for Speaker Verification with Speaker-Text Factorized Embeddings
• Channel Invariant Speaker Embedding Learning with Joint Multi-Task and Adversarial Training
• Investigation of Specaugment for Deep Speaker Embedding Learning
• Discriminative Neural Embedding Learning for Short-Duration Text-Independent Speaker Verification
• Margin matters: Towards more discriminative deep neural network embeddings for speaker recognition
• The SJTU Robust Anti-Spoofing System for the ASVspoof 2019 Challenge
• Cross-Domain Replay Spoofing Attack Detection Using Domain Adversarial Training
• Data Augmentation Using Variational Autoencoder for Embedding Based Speaker Verification
• On the Usage of Phonetic Information for Text-independent Speaker Embedding Extraction
• Angular Softmax for Short-Duration Text-independent Speaker Verification.
• Covariance based deep feature for text-dependent speaker verification
• Generative Adversarial Networks based X-vector Augmentation for Robust Probabilistic Linear Discriminant Analysis in Speaker Verification
• Focal KL-divergence based dilated convolutional neural networks for co-channel speaker identification