rohitrango/objects-that-sound
Unofficial Implementation of Google Deepmind's paper `Objects that Sound`
This project helps you find similar video frames or identify what an audio clip sounds like, even if you don't have descriptions. You provide video and audio clips, and it processes them to allow you to search for visually similar frames or find frames that match a particular sound. This tool is for researchers or media catalogers working with large collections of unlabeled audio-visual data.
No commits in the last 6 months.
Use this if you need to quickly retrieve relevant video frames based on either a visual example or an audio snippet, especially in large, unsorted multimedia archives.
Not ideal if you need precise localization of sound sources within a video or if your data isn't primarily focused on musical instruments or distinct sound events.
Stars
83
Forks
16
Language
Python
License
—
Category
Last pushed
May 07, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/rohitrango/objects-that-sound"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
erdogant/KNRscore
KNRScore is a Python package for computing K-Nearest-Rank Similarity, a metric that quantifies...
reppertj/earworm
Search for music by sonic similarity
prabal-rje/latentscore
Python library for generating ambient music from text descriptions. No GPU required. Turn text...
FabianGroeger96/deep-embedded-music
Creation of an embedding space using unsupervised triplet loss and Tile2Vec that can be used for...
drscotthawley/audio-algebra
alchemy with embeddings