Papers › Hello Edge: Keyword Spotting on Microcontrollers

Hello Edge: Keyword Spotting on Microcontrollers

20 Nov 2017arXiv:1711.07128archive 2025-07-28

Yundong Zhang, Naveen Suda, Liangzhen Lai, Vikas Chandra

Keyword spotting (KWS) is a critical component for enabling speech based user interactions on smart devices. It requires real-time response and high accuracy for good user experience. Recently, neural networks have become an attractive choice for KWS architecture because of their superior accuracy compared to traditional speech processing algorithms. Due to its always-on nature, KWS application has highly constrained power budget and typically runs on tiny microcontrollers with limited memory and compute capability. The design of neural network architecture for KWS must consider these constraints. In this work, we perform neural network architecture evaluation and exploration for running KWS on resource-constrained microcontrollers. We train various neural network architectures for keyword spotting published in literature to compare their accuracy and memory/compute requirements. We show that it is possible to optimize these neural network architectures to fit within the memory and compute constraints of microcontrollers without sacrificing accuracy. We further explore the depthwise separable convolutional neural network (DS-CNN) and compare it against other neural network architectures. DS-CNN achieves an accuracy of 95.4%, which is ~10% higher than the DNN model with similar number of parameters.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

18 repositories listed; official and paper-mentioned ones first.

ARM-software/ML-KWS-for-MCU officialmentioned in papermentioned on GitHubtf report
BgLoveXixi/Keyword_recognition mentioned on GitHubtf report
Jaskaran197/KWS-TF-MCU mentioned on GitHubtf report
Lebhoryi/ML-KWS-for-MCU mentioned on GitHubtf report
Paulonso/ARM-software mentioned on GitHubtf report
Paulonso/ML-KWS-for-MCU mentioned on GitHubtf report
UT2UH/ML-KWS-for-ESP32 mentioned on GitHubtf report
etrommer/dcsr mentioned on GitHubtf report
fracorti/reds mentioned on GitHubtf report
hustxsl/C-ML-KWS-for-MCU mentioned on GitHubtf report
jayant766/MIDAS-IIITD mentioned on GitHubtf report
magahub/KWS-ARM mentioned on GitHubtf report
robin-ai-ml/ML-KWS-for-MCU mentioned on GitHubtf report
widzemin/audio_project mentioned on GitHubtf 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 Spotting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keyword Spotting Google Speech Commands DS-CNN Google Speech Commands V1 12 94.4 #14 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands GRU Google Speech Commands V1 12 93.5 #15 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands LSTM Google Speech Commands V1 12 92.9 #16 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands Basic LSTM Google Speech Commands V1 12 92.0 #17 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands DNN Google Speech Commands V1 12 91.6 #18 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands CNN Google Speech Commands V1 12 84.6 #19 of 42 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Batch NormalizationDilated ConvolutionResidual Connection

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