Abstract Automatic Speech Recognition (ASR) system is an emerging technology used in
various fields such as robotics, traffic controls, and healthcare, etc. The leading cause of …

Transformer-based language models such as BERT provide significant accuracy
improvement to a multitude of natural language processing (NLP) tasks. However, their hefty …

Block floating point (BFP), an efficient numerical system for deep neural networks (DNNs),
achieves a good trade-off between dynamic range and hardware costs. Specifically, prior …

General speech recognition models require large capacity and strong computing power.
Based on small capacity and low computing power to realize speech analysis and semantic …

Specialized hardware accelerators have been developed to enhance power-performance
efficiency for Deep Neural Network (DNN) applications. A primary challenge in DNN …

The twilight of Dennard scaling has activated a global trend towards application-based
hardware specialization. This trend is currently accelerating due to the surging …