Assessing the adequate treatment of fast speech in unit selection speech synthesis systems for the visually impaired

This paper describes work in progress concerning the adequate modeling of fast speech in unit selection speech synthesis systems – mostly having in mind blind and visually impaired users. Initially, a survey of the main phonetic characteristics of fast speech will be given. From this, certain conclusions concerning an adequate modeling of fast speech in unit selection synthesis will be drawn. Subsequently, a questionnaire assessing synthetic speech related preferences of visually impaired users will be presented. The last section deals with future experiments aiming at a definition of criteria for the development of synthesis corpora modeling fast speech within the unit selection paradigm.