Rethinking Speaker Embeddings for Speech Generation: Sub-Center Modeling for Capturing Intra-Speaker Diversity
This work revisits this design choice and proposes a sub-center modeling framework for speaker embeddings, which improves intelligibility, increases pitch variability, achieves higher naturalness ratings, and retains strong speaker verification performance in zero-shot voice conversion.
Ismail Rasim Ulgen, J. Hansen, Carlos Busso et al.
· 0 citations