Dear all,
It is said on hts website that "HTS version 2.2 includes deterministic annealing EM algorithm in parameter estimation step, KLD-based state-mapping and cross-lingual speaker adaptation, minimum generation error (MGE) training, and other minor new features. "
Here is the question, how can I test " KLD-based state-mapping and cross-lingual speaker adaptation", is there any demos I can run?
Thanks a lot.