BiometricVox/DAE_SpeakerID

Denoising autoencoders for speaker identification on MCE 2018 challenge

35
/ 100
Emerging

This project helps identify specific speakers from speech segments, particularly in call center conversations, even when there's variability in how people speak over time. You provide existing speaker profiles (ivectors) and new speech segments, and it tells you if a blacklisted speaker is present and, if so, which one. This is for professionals in fields like security, forensics, or customer service who need to automate speaker identification.

No commits in the last 6 months.

Use this if you need to reliably identify known speakers from short speech segments in a noisy environment, such as in call center recordings, to screen against a blacklist.

Not ideal if you need to identify speakers from raw audio files, as this project requires pre-processed ivector data.

speaker-identification voice-biometrics call-center-analytics forensic-audio security-screening
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

12

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Nov 08, 2018

Commits (30d)

0

Get this data via API

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

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