Heinrich Dinkel

speaker verification (3) voice activity detection (2) convolutional neural network (2) transfer learning (2) adversarial training (2) audio encoder (2) knowledge distillation (2) audio tagging (2) domain adaptation (2) weakly supervised learning (1) cross-modal retrieval (1) self-supervised learning (1) keyword spotting (1) spoofing detection (1) feature learning (1) model architecture (1) audio-text retrieval (1) text representation (1) biometric authentication (1) anti-spoofing (1)