Varun Nagaraja

model compression (1) multi-task learning (1) transfer learning (1) knowledge distillation (1) speech recognition (1) keyword spotting (1) singular value decomposition (1) collaborative learning (1) latency optimization (1) joint training (1) word error rate (1) time delay neural network (1) acoustic encoder (1) on-device speech recognition (1) dynamic encoder transducer (1) layer dropout (1) encoder layer (1) collaborative training (1) dynamic encoder (1) sequence transducer (1)