ArchitParnami/Few-Shot-KWS

Few-Shot Keyword Spotting

36
/ 100
Emerging

This project helps audio engineers or product developers build wake-word or voice command systems with very little training data. It takes in short audio clips of spoken keywords and, using a few examples, can identify new occurrences of those keywords. This is ideal for quickly adding new voice commands to devices or applications without extensive data collection.

No commits in the last 6 months.

Use this if you need to quickly implement a keyword spotting system for new or niche commands using only a handful of audio samples.

Not ideal if you require a system that can understand a wide range of natural language phrases or continuous speech.

voice-interface-design audio-analysis wake-word-detection embedded-systems speech-recognition
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

71

Forks

17

Language

Jupyter Notebook

License

Last pushed

Apr 11, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ArchitParnami/Few-Shot-KWS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.