ArchitParnami/Few-Shot-KWS
Few-Shot Keyword Spotting
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.
Stars
71
Forks
17
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
Picovoice/porcupine
On-device wake word detection powered by deep learning
MycroftAI/mycroft-precise
A lightweight, simple-to-use, RNN wake word listener
arcosoph/nanowakeword
A lightweight, open-source, and intelligent wake word detection engine. Train custom,...
mozilla/DeepSpeech
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run...
OAID/cortex-m-kws
Cortex M KWS example with Tengine Lite.