Assigning phrase breaks using CARTs for Basque TTS
Eva Navas,
Inmaculada Hernáez,
Nerea Ezeiza
Abstract:This paper presents a prosodic phrasing method for the Basque language, to improve naturalness in text to speech synthesis. Binary classification trees are trained with morphological and syntactic information to predict locations of breaks. Overall score achieved by the prediction tree is 92.53%, which compares positively with the results published for other languages.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.