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.
Cioflan, C., Cavigelli, L., Rusci, M., de Prado, M., Benini, L. (2022). Towards On-device Domain Adaptation for Noise-Robust Keyword Spotting. 345 E 47TH ST, NEW YORK, NY 10017 USA : IEEE [10.1109/AICAS54282.2022.9869990].
Towards On-device Domain Adaptation for Noise-Robust Keyword Spotting
Rusci, M;Benini, L
2022
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
