YuanGongND/psla

Code for the TASLP paper "PSLA: Improving Audio Tagging With Pretraining, Sampling, Labeling, and Aggregation".

39
/ 100
Emerging

This project helps audio engineers and researchers automatically identify and label sounds within long audio recordings. It takes raw audio files as input and outputs detailed tags describing the sounds present, even for very long recordings. Anyone working with large audio datasets who needs to categorize or analyze sound events can use this tool.

149 stars. No commits in the last 6 months.

Use this if you need to accurately identify and tag sound events in extensive audio collections, such as environmental recordings or broadcast archives, and want state-of-the-art performance with efficient resource use.

Not ideal if your primary goal is to analyze human speech, musical content, or very specific, niche audio events that require highly specialized models.

audio-analysis sound-recognition acoustic-monitoring media-asset-management environmental-soundscapes
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

149

Forks

15

Language

Python

License

BSD-3-Clause

Last pushed

Jul 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YuanGongND/psla"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.