YChenL/UniVR

An official implement of "UniVR: A Unified Framework for Pitch-Shifted Voice Restoration in Speaker Identification"

26
/ 100
Experimental

If you work with speaker identification systems, this project helps restore the quality of voice recordings that have been intentionally or unintentionally pitch-shifted. It takes in these altered voice samples and outputs restored versions, making it easier for your speaker identification system to accurately recognize individuals. This is designed for researchers and engineers developing or utilizing speaker identification technologies.

No commits in the last 6 months.

Use this if you need to improve the accuracy of speaker identification when dealing with voice recordings that have had their pitch altered.

Not ideal if your primary challenge is noise reduction or accent variability, rather than pitch-shifting, in voice recordings.

speaker-identification voice-biometrics audio-forensics speech-processing voice-restoration
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Jupyter Notebook

License

Last pushed

Aug 31, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/YChenL/UniVR"

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