SBIR-STTR Award

The nonspeaking suffer from a lack of natural-sounding synthetic voices that are appropriate in terms of age, sex, and dialect. The creation of a wide range of natural-sounding voices has been hampered by high development costs resulting from a lack of adequate linguistic models and flexible software tools for text-to-speech synthesis. Eloquent Technology, Inc. (ETI) proposes a novel modular approach to rule-based speech synthesis coupled with a new synthesis model that will lead to cost-effective development of high-quality synthetic voices for the nonspeaking. The key tool in this approach is Delta, a programming language developed by ETI for expressing text-to-speech algorithms (rules). 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 synthesis model uses Delta's innovative "multi-stream" data structure for representing utterances. In this Phase I project, we will test the feasibility of the modular approach by implementing a base rule set for English, and voice modules for two American dialects.Anticipated Results and

Potential Commercial Applications:
Completion of Phase II of this project will result in a variety of natural-sounding synthetic male, female, and child voices for several dialects of American English, for incorporation into speaking devices for the nonvocal. The methodology and linguistic models developed in this work will enable rapid, cost-effective production of new customized voices. The approach we develop for synthesis of English will also be applicable to other languages. More general applications of our technology include: telephone access to computer systems, navigation and warning systems for automobiles, integrated voice applications in office information systems, speech accompaniment to computer displays, electronic mail, and others.Key Words: Nonspeaking, Speech Synthesis, Text-to-speech, Voice, Speech, Synthesis by Rule, Nonvocal, PhoneticsTopic 1: Development or Adaptation of Devices Mechanisms, or Techniques for Disabled Individuals

Eloquent Technology, Inc. (a al) proposes Develop text- to-speech synthesis software for six regional dialects of American English and BlackEnglish, for use in unlimited vocabulary vocal communication aids. ETI will use rule-based synthesis with a novel modular approach and phonetic model that promise for the first time, costSicient development of a broad range of high-quality synthetic voices.For each dialect, both text-to-phoneme and phoneme-to-speech rules will contain substantial universal modules common to all dialers, plus much smaller dialect-specific modules. With the resulting structure, relatively little effort will be required to add further dialects in the future. Additional modules could generate differentages and sexes.The critical software tool for the project is ETI's Delta System, specially designed to expedite speech synthesis rule development. Deltawvides a powerful interactive environment for exploring rules with immediate auditory feedback and a full-featured programming language with accompanying debugger for implementing and testing the rules. Delta programs are compiled into a portable format for use in end-products on a varier of cpu's.

Keywords:
speech-impaired, speech synthesis, at-to-speech, vocal communication aids, synthesis by rule, nonvocal, altemadve/augmentative communication aids, speech processingAnticipated results, Impilcatlons, and commercial appilcatlons:Completion of this project will result in a variety of natutal- sounding synthetic voices in several dialects of American English, for incorporation into alternative/augmentative communication aids for speech-impaired people. The methodology and linguistic models developed in this work will also lay the foundation for rapid, cost-effective production of new voices in different dialects, ages, and sexes. The approach we develop for synthesis of English will also be applicable to other languages. More general applications of our technology include: telephone access to computer systems, navigation and warning systems for automobiles, integrated voice applications in office information systems, speech accompaniment to computer displays, electronic mail, and others.Topic 1: Development or Adaptation of Devices, Mechanisrns, or Techniques for Disabled Individuals