On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systems
METADATA ONLY
Loading...
Author / Producer
Date
2024
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Keyword spotting accuracy degrades when neural networks are exposed to noisy environments. On-site adaptation to previously unseen noise is crucial to recovering accuracy loss, and on-device learning is required to ensure that the adaptation process happens entirely on the edge device. In this work, we propose a fully on-device domain adaptation system achieving up to 14% accuracy gains over already-robust keyword spotting models. We enable on-device learning with less than 10 kB of memory, using only 100 labeled utterances to recover 5% accuracy after adapting to the complex speech noise. We demonstrate that domain adaptation can be achieved on ultra-low-power microcontrollers with as little as 806mJ in only 14 s on always-on, battery-operated devices.
Permanent link
Publication status
published
Editor
Book title
2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS)
Journal / series
Volume
Pages / Article No.
6 - 10
Publisher
IEEE
Event
6th IEEE International Conference on AI Circuits and Systems (AICAS 2024)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
On-Device Learning; Domain Adaptation; Low-Power Microcontrollers; Extreme Edge; TinyML; Noise Robustness; Keyword Spotting
Organisational unit
03996 - Benini, Luca / Benini, Luca