mayurnewase/looking-to-listen-at-cocktail-party
Looking to listen at cocktail party
This project helps you isolate and understand speech from a specific person in a video, even when there's a lot of background noise or other people talking. You provide videos with multiple speakers and background sounds, and it outputs the clear, separated speech of the person you're focused on. This is for anyone who needs to extract clear audio from noisy video recordings, like researchers analyzing interviews or content creators cleaning up dialogue.
No commits in the last 6 months.
Use this if you need to separate the voice of a particular speaker from a video where multiple people are speaking or there's significant ambient noise.
Not ideal if you only have audio recordings without corresponding video, or if you need to process large volumes of real-time audio.
Stars
36
Forks
10
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mayurnewase/looking-to-listen-at-cocktail-party"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/audio
Data manipulation and transformation for audio signal processing, powered by PyTorch
asteroid-team/asteroid
The PyTorch-based audio source separation toolkit for researchers
deezer/spleeter
Deezer source separation library including pretrained models.
audeering/opensmile
The Munich Open-Source Large-Scale Multimedia Feature Extractor
audeering/opensmile-python
Python package for openSMILE