Pedro J. Moreno

automatic speech recognition (5) data augmentation (4) semi-supervised learning (2) voice conversion (2) multilingual automatic speech recognition (2) word error rate (2) text-to-speech synthesis (2) speech recognition (2) knowledge distillation (1) model architecture (1) attention mechanism (1) multi-modal learning (1) text representation (1) adversarial training (1) neural vocoder (1) self-supervised learning (1) generative adversarial network (1) semi-supervised training (1) modality alignment (1) speech separation (1)