XiaoHui Zhang

audio deepfake detection (3) catastrophic forgetting (3) continual learning (3) speech recognition (2) representation learning (2) weight modification (2) gradient modification (2) feature distribution (2) automatic speech recognition (2) language identification (1) multimodal learning (1) stochastic gradient descent (1) speech synthesis (1) acoustic model (1) self-supervised learning (1) connectionist temporal classification (1) fisher information (1) neural network optimization (1) adversarial training (1) feature extraction (1)