A KWS System for Edge-Computing Applications with Analog-Based Feature Extraction and Learned Step Size Quantized Classifier

A KWS System for Edge-Computing Applications with Analog-Based Feature Extraction and Learned Step Size Quantized Classifier

Edge-computing applications demand ultra-low-power architectures for both feature extraction and classification tasks. In this manuscript, a Keyword Spotting (KWS) system tailored for energy-constrained portable environments is proposed. A 16-channel analog filter bank is employed for audio feature...

Full description

Saved in:
Bibliographic Details
Main Authors: Yukai Shen, Binyi Wu, Dietmar Straeussnigg, Eric Gutierrez
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
keyword spotting (KWS)
quantization-aware training (QAT)
analog feature extraction
recurrent neural network (RNN)
edge computing
Online Access:https://www.mdpi.com/1424-8220/25/8/2550
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items