Erik Visser

audio understanding (2) multi-task learning (1) curriculum learning (1) self-supervised learning (1) knowledge distillation (1) temporal reasoning (1) question answering (1) automatic speech recognition (1) intent classification (1) speaker diarization (1) text-to-speech synthesis (1) large audio language model (1) text-to-audio generation (1) speech representation learning (1) audio event detection (1) large language model (1) audio question answering (1) music identification (1) model compression (1) text-to-speech generation (1)