Multi-variety adaptive acoustic modeling in HSMM-based speech synthesis

In this paper we apply adaptive modeling methods in Hidden Semi-Markov Model (HSMM) based speech synthesis to the modeling of three different varieties, namely standard Austrian German, one Middle Bavarian (Upper Austria, Bad Goisern), and one South Bavarian (East Tyrol, Innervillgraten) dialect. We investigate different adaptation methods like dialectadaptive training and dialect clustering that can exploit the common phone sets of dialects and standard, as well as speakerdependent modeling. We show that most adaptive and speakerdependent methods achieve a good score on overall (speaker and variety) similarity. Concerning overall quality there is no significant difference between adaptive methods and speakerdependent methods in general for the present data set.