This study explores the impact of various layers of the XLS-R encoder on speaker recognition accuracy using CNNs and logistic regression. Findings indicate that earlier layers yield higher accuracy, highlighting their importance in feature capture. The study also reveals a significant gender disparity in accuracy. These results suggest the need for further investigation into model biases and optimizations.
-
Notifications
You must be signed in to change notification settings - Fork 0
slinusc/speaker_recognition_evaluation
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Investigating Layer-Specific Performance in Speaker Recognition with XLS-R Architecture
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published