Papers › Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors

Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors

22 Aug 2024arXiv:2408.12481archive 2025-07-28

Manuele Rusci, Francesco Paci, Marco Fariselli, Eric Flamand, Tinne Tuytelaars

This paper proposes a self-learning method to incrementally train (fine-tune) a personalized Keyword Spotting (KWS) model after the deployment on ultra-low power smart audio sensors. We address the fundamental problem of the absence of labeled training data by assigning pseudo-labels to the new recorded audio frames based on a similarity score with respect to few user recordings. By experimenting with multiple KWS models with a number of parameters up to 0.5M on two public datasets, we show an accuracy improvement of up to +19.2% and +16.0% vs. the initial models pretrained on a large set of generic keywords. The labeling task is demonstrated on a sensor system composed of a low-power microphone and an energy-efficient Microcontroller (MCU). By efficiently exploiting the heterogeneous processing engines of the MCU, the always-on labeling task runs in real-time with an average power cost of up to 8.2 mW. On the same platform, we estimate an energy cost for on-device training 10x lower than the labeling energy if sampling a new utterance every 6.1 s or 18.8 s with a DS-CNN-S or a DS-CNN-M model. Our empirical result paves the way to self-adaptive personalized KWS sensors at the extreme edge.

PaperPDFCode

Code

mrusci/ondevice-fewshot-kws mentioned on GitHubpytorch report
mrusci/ondevice-learning-kws mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Keyword SpottingSelf-Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SETSelf-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections