Severely speech-impaired individuals need communication devices that provide natural-sounding syynthetic voices that are appropriate in terms of sex, age, nationally, and dialect. Thecreation of such voices has been hampered by high development costs resulting from a lack of flexible software tools and adequate linguistic models for text-to-speech synthesis. Eloquent Technology, Inc(ETI) proposes a novel modular approach to rulebased speech synthesis intended to reduce development costs for high-quality synthetic voices. The key tool in this approach is ETI's Delta System, a programming language and interactive development environment for developing text-tospeech algorithms. In the modular approach, a single program module(the base module) builds the part of an utterance representation common to all voices in a given language; smaller, independent voice modules produce the variations among the voices. The linguistic model on which the synthesis rules will be based uses Delta's innovative multistream data structure for representing utterances. In Phase I, the feasibility of the modular approach will be tested by implementing a base module for English and voice modules for two American dialectsAwardee's statement of the potential commercial applications of the research:Commercial applications include: vocal communication aids for severely vocally impaired persons, reading machines and computer screen readers for blind and dyslexic persons, telephone access to computer systems, electronic mail, "head-up" instructions, navigation and warning systems for automobiles and airplanes, integrated voice applications in office information systems, and others. The approach developed for the synthesis of English will also be applicable to other languagesNational Institute on Deafness and Other Communication Disorders (NICDC)
