Sefik Emre Eskimez

speech enhancement (4) automatic speech recognition (3) speaker embedding (2) speech recognition (2) speech separation (2) federated learning (2) multi-task learning (2) gradient aggregation (1) voice conversion (1) one-shot learning (1) data augmentation (1) knowledge distillation (1) semi-supervised learning (1) attention mechanism (1) deep learning (1) flow matching (1) self-supervised learning (1) zero-shot learning (1) speaker verification (1) model compression (1)