Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency

Facebook NLP Research

Abstract

We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or fine-tuning. To trading off accuracy and latency, DET assigns different encoders to decode different parts of an utterance. We apply and compare the layer dropout and the collaborative learning

 

 

To finish reading, please visit source site