Project AURIONAI Use-Cases Research & Innovation
Arm
TinyMLfamily

Hello Edge keyword spotting models

Keyword spotting network families compared for microcontrollers in the Hello Edge study. Arm publishes the trained models in its ML-Zoo for Cortex-M and Ethos-U targets.

ArmArm
Figure from the Hello Edge keyword spotting models paper: Keyword spotting pipeline.
Levelfamily
ClassTinyML
Parametersnot in the notes
Contextnot in the notes
Released20 Nov 2017
Opennessunknown
Runs onmicrocontroller
Statusactive

Lineage

ArmHello Edge KWS CNN (small, medium, large) belongs to this familyTinyML20 Nov 2017
ArmHello Edge KWS DNN (small, medium, large) belongs to this familyTinyML20 Nov 2017
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Keyword spotting and audio event detection on microcontrollersexemplarTinyML on microcontrollersproduced by

Identity

Developer
Arm
Family
not in the notes
Released
20 Nov 2017 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
Arm ML-Zoo ships CNN, DNN and DS-CNN keyword models in small, medium and large sizes (INT8 and FP32 TFLite). DS-CNN is held as its own AURION record (ds-cnn).
Context length
not in the notes
Input
audio
Output
labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
microcontroller
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/1711.07128 https://arxiv.org/abs/1711.07128
  2. github.com/ARM-software/ML-zoo/tree/master/models/keywor... https://github.com/ARM-software/ML-zoo/tree/master/models/keyword_spotting

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Hello Edge Keyword Spotting Models", https://aurion.semai.id/models/arm-hello-edge-kws/, records of October 2026.