Aparna Khare

automatic speech recognition (3) multi-task learning (2) transfer learning (2) multimodal learning (2) visual grounding (1) multitask learning (1) keyword spotting (1) audio visual (1) deep neural network (1) model fine-tuning (1) unsupervised pre-training (1) transformer encoder (1) audiovisual speech recognition (1) keyword detection (1) crossmodal attention (1) person identification (1) multi-modal pre-training (1) multi-modal embedding (1) weighted cross-entropy (1) multimodal speech recognition (1)