AI engineering glossary · Generative media multimodal
What is VAD (voice activity detection)?
Voice activity detection (also called VAD): Detecting which parts of an audio stream contain human speech and which are silence or background noise. It saves compute, trims recordings and decides when a user has stopped talking in voice assistants.
Voice activity detection: an example
A voice bot waits until the detector reports 700 ms of silence before treating the customer's turn as finished.
Related terms
- Streaming ASR
- Speaker diarisation
- Automatic speech recognition
More Generative media multimodal terms
- Voice cloning
- VQ-VAE
- Wasserstein GAN
- Watermarking generated content
- wav2vec 2.0
- WaveNet
- Whisper
- Zero-shot TTS
Where you learn it
Voice activity detection is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.