Towards On-device Domain Adaptation for Noise-Robust Keyword Spotting


METADATA ONLY
Loading...

Date

2022

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

The accuracy of a keyword spotting model deployed on embedded devices often degrades when the system is exposed to real environments with significant noise. In this paper, we explore a methodology for tailoring a model to on-site noises through on-device domain adaptation, while accounting 14 the edge computing-associated costs. We show that accuracy improvements by up to 18% can be obtained by specialising on difficult, previously unseen noise types, on embedded devices with a power budget in the Watt range, with a storage requirement of 1.1GB. We also demonstrate an accuracy improvement of 1.43% on an ultra-low power platform consuming few-10 mW, requiring only 1.47 MB of memory kw the adaptation stage, at a one-time energy cost of 5.81J.

Publication status

published

Editor

Book title

IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

Journal / series

Volume

Pages / Article No.

82 - 85

Publisher

IEEE

Event

IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS 2022)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03996 - Benini, Luca / Benini, Luca check_circle

Notes

Funding

Related publications and datasets