Reference app: Keyword Spotting (KWS) on Cortex-M
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
Description
Build a complete reference application for keyword spotting (DS-CNN) on Cortex-M. Includes audio preprocessing, model inference, and post-processing.
Acceptance Criteria
- End-to-end KWS app running on Cortex-M55 (FVP and/or hardware)
- Audio input -> keyword classification output pipeline working
- Latency and memory footprint documented
- README with build and run instructions
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or entry points. Start by locating the Cortex-M55/FVP reference-app entry point and the audio preprocessing, inference, and post-processing paths. Done means the end-to-end KWS pipeline runs on FVP or hardware, latency and memory are documented, and a README explains how to build and run it.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- machine-learning
- Domain
- embedded-iot, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100