KunHanKH/GE2E_Speaker_Verification

Most Complete Pytorch Imeplementation "GENERALIZED END-TO-END LOSS FOR SPEAKER VERIFICATION"

26
/ 100
Experimental

This project helps researchers and developers create and evaluate robust speaker verification systems. It takes raw audio data from speech datasets like TIMIT or keyword spotting datasets and processes it to identify or authenticate speakers, even with limited speech samples or varying background noise. The primary users are researchers or engineers working on voice authentication, security systems, or speech recognition applications.

No commits in the last 6 months.

Use this if you are building or researching speaker verification systems and need to train models that can accurately identify individuals based on their voice, regardless of what they say.

Not ideal if you need a pre-built, production-ready speaker verification API or solution, as this project is an implementation for research and development.

voice-biometrics speech-recognition-research speaker-authentication audio-analytics voice-security
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

10

Forks

2

Language

Jupyter Notebook

License

Last pushed

Mar 11, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/KunHanKH/GE2E_Speaker_Verification"

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