Seung-Bin Kim

speaker verification (4) raw waveform (3) speaker embedding (3) self-supervised learning (2) speech synthesis (2) text-to-speech synthesis (2) teacher-student learning (2) diffusion transformer (1) representation alignment (1) attention mechanism (1) variational autoencoder (1) cross-attention mechanism (1) speech representation (1) multi-head attention (1) deep neural network (1) sound event detection (1) adversarial network (1) convolutional neural network (1) prototypical network (1) noise robustness (1)