K. Lee

Uncertainty-aware methods can significantly enhance speaker verification performance by reducing EER and improving separation through a unified approach that propagates uncertainty throughout the verification pipeline.

Replacing standard residual connections with manifold-constrained hyper-connections boosts speaker recognition performance across multiple architectures.

Uncertainty estimates in speaker recognition can be dramatically improved by incorporating both inter- and intra-speaker dynamics, leading to more reliable embeddings.

Speaker recognition accuracy improves dramatically when leveraging a U-Net-based fusion of noisy and enhanced speech, coupled with a novel training strategy.