Modern smart glasses leverage advanced audio sensing and machine learnin...
Automatic Speech Recognition (ASR) models need to be optimized for speci...
This paper proposes a hardware-efficient architecture, Linearized Convol...
The unified streaming and non-streaming two-pass (U2) end-to-end model f...
In this paper, we present a new open source, production first and produc...
In this paper, we present a novel two-pass approach to unify streaming a...
This chapter deals with multi-material flow problems by a kind of effect...
When describing the deflagration-to-detonation transition in solid granu...
Recurrent Neural Networks (RNNs) have dominated language modeling becaus...
Visual object recognition under situations in which the direct line-of-s...
Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) ...