Explainable Speaker Recognition
-
Updated
Oct 26, 2022 - Python
Explainable Speaker Recognition
This is a speaker verification system uses Total Variability and Projection Matrix. Intersession variability was compensated by using backend procedures, such as linear discriminant analysis (LDA) and within-class covariance normalization (WCCN), followed by a scoring, the cosine similarity score. In literature this approach named i-vectors.
Add a description, image, and links to the forensic-speaker-recognition topic page so that developers can more easily learn about it.
To associate your repository with the forensic-speaker-recognition topic, visit your repo's landing page and select "manage topics."