Yan Wen

synthetic speech detection (2) speaker verification (2) gaussian mixture model (2) policy gradient (1) sample complexity (1) deepfake detection (1) model merging (1) robust reinforcement learning (1) minimax optimization (1) multilingual machine translation (1) speaker recognition (1) diffusion model (1) convolutional neural network (1) parameter-efficient fine-tuning (1) general utility (1) denoising process (1) low-bit quantization (1) residual network (1) stochastic method (1) mobile network (1)