Several Aspects of Machine-Driven Phrasing in Text-to-Speech Systems

Several Aspects of Machine-Driven Phrasing in Text-to-Speech Systems The article discusses differences between a priori and a posteriori phrasing and their importance in the task of automatic prosodic phrasing in text-to-speech systems. On several examples it illustrates shortcomings of common evaluation of a priori phrasing performance using a posteriori phrasing of referential corpus data. The paper also proposes and evaluates a method for a priori phrasing based on template matching of quasi-syntactical representations of sentences.