jtkim-kaist/VAD

Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.

43
/ 100
Emerging

This toolkit helps signal processing researchers and audio engineers accurately identify when speech is present in an audio recording, distinguishing it from background noise or silence. It takes raw audio recordings as input and outputs precise timestamps or labels indicating speech segments. This is ideal for anyone working with spoken language data where precise speech detection is crucial for further analysis or processing.

869 stars. No commits in the last 6 months.

Use this if you need to reliably separate speech from non-speech in noisy real-world audio, especially for research or advanced audio processing applications.

Not ideal if you're looking for a simple, off-the-shelf voice recorder or transcription service without needing to understand the underlying speech detection models.

speech-processing audio-analysis signal-processing noise-reduction speech-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 25 / 25

How are scores calculated?

Stars

869

Forks

233

Language

MATLAB

License

Last pushed

Jun 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jtkim-kaist/VAD"

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