Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion
Two geometric regularization strategies (hinged Riesz log-energy and effective-dimension maximization) applied to classifier prototypes to encourage more uniform hyperspherical coverage are investigated and the resulting prototype sets exhibit higher effective dimensionality and improved isotropy.
Mathilde Abrassart, Nicolas Obin, Axel Roebel
· 0 citations