EERA-KWS: A 163 TOPS/W Always-on Keyword Spotting Accelerator in 28nm CMOS Using Binary Weight Network and Precision Self-Adaptive Approximate Computing

EERA-KWS: A 163 TOPS/W Always-on Keyword Spotting Accelerator in 28nm CMOS Using Binary Weight Network and Precision Self-Adaptive Approximate Computing

This paper proposed an energy-efficient reconfigurable accelerator for keyword spotting (EERA-KWS) based on binary weight network (BWN) and fabricated in 28-nm CMOS technology. This keyword spotting system consists of two parts: the feature extraction based on melscale frequency cepstral coefficient...

Full description

Bibliographic Details
Main Authors: Bo Liu, Zhen Wang, Hu Fan, Jing Yang, Wentao Zhu, Lepeng Huang, Yu Gong, Wei Ge, Longxing Shi
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Keyword spotting
binary weight network
approximate computing
Online Access:https://ieeexplore.ieee.org/document/8743369/

Internet

https://ieeexplore.ieee.org/document/8743369/

Similar Items