Human-like cross-language generalisation in deep neural speaker embeddings and its acoustic foundations
Generalisability is a central question for deep neural networks, including the cross-language generalisation of speaker embeddings. This study examined whether deep neural speaker embeddings generalise across languages and how such generalisation relates to human perception and acoustic structure.
By Tianze Xu, Xiyang Li, Xiaoming Jiang, Volker DellwoarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Nov 5, 2026.
Comments
Sign in to join the discussion.