nicklashansen/voice-activity-detection
Voice Activity Detection (VAD) using deep learning.
This tool helps systems identify when someone is speaking in audio recordings, even in very noisy environments. It takes raw audio data, often with background noise, and outputs markers indicating the precise segments where speech is present. Anyone building or managing automated speech recognition (ASR) systems, voice assistants, or call center analytics would find this useful to improve accuracy and reduce processing power.
204 stars. No commits in the last 6 months.
Use this if you need to reliably detect human speech in audio streams that frequently contain significant background noise, such as in busy offices, public spaces, or industrial settings.
Not ideal if your audio environments are consistently quiet and clean, as simpler, less computationally intensive methods might suffice.
Stars
204
Forks
34
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Oct 14, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nicklashansen/voice-activity-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.