hongfeixue/KWS_pytorch

Keyword spotting, Speech wake_up, by pytorch, DNN, CNN, TDNN, DFSMN, LSTM

32
/ 100
Emerging

This project helps you build and evaluate systems that listen for specific "wake-up words" or keywords in spoken audio. You provide audio files labeled with keywords (or wake-up phrases like "Hi xiaowen"), and it generates models that can identify these words in new audio. This is useful for product managers, voice UI designers, or hardware engineers developing smart devices, accessibility tools, or interactive voice response systems.

No commits in the last 6 months.

Use this if you need to develop or experiment with models that can reliably detect predefined keywords or wake-up phrases from audio input, similar to how smart speakers activate.

Not ideal if you need a system for general speech-to-text transcription, speaker identification, or natural language understanding beyond simple keyword detection.

voice-user-interface smart-devices audio-analytics speech-recognition accessibility-tech
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

53

Forks

10

Language

Python

License

Last pushed

Mar 15, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hongfeixue/KWS_pytorch"

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