HumlaGlossary
What is Voice activity detection (VAD)?
Voice activity detection is the technique of detecting when someone is actually speaking in an audio stream, as opposed to silence or background noise.
Free · Open source · macOS 13+ (Apple Silicon)
In depth
What it means.
- It's used to split a recording into speech segments and to avoid transcribing silence, which improves accuracy and reduces cost.
- Humla uses VAD to cut each recording into chunks at natural speech pauses, so transcription stays clean and hallucinations from silence are reduced.
Related