Papers › Hello Edge: Keyword Spotting on Microcontrollers
Hello Edge: Keyword Spotting on Microcontrollers
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.
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.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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