A taxonomy of computer-based speech training systems is presented, based on the physical source of feedback, standards of evaluation, level and type of detail on which feedback is based, and the form and instructional context of feedback. Reasons for selecting a particular approach are discussed in relation to existing systems. (Author/JDD)

Design considerations for speech training systems include the types of information about speech to be used in training, whether acoustic or physiologic; and the use of models of speech production, whether partially perceptual and partially knowledge-based or explicit data-based models. A taxonomy of speech training systems is presented.…

This study evaluated the accuracy of automated methods of grammatical categorization ("tagging") of transcribed conversational language samples from 30 normally developing children. On a word-by-word basis, automated accuracy levels averaged 95.1%; accuracy of tagging whole utterances averaged 77.7%. Results suggest that further improvement of…

This sourcebook is intended to provide researchers and users of natural language computer systems with a classification scheme to describe language-related problems associated with such systems. Methods from the disciplines of artificial intelligence (AI), education, linguistics, psychology, anthropology, and psychometrics were applied in an…

While traditional views of literacy assume that discourse is either written or oral, an alternative perspective considers different discourse samples as part of the linguistic repertoire of the speech community. Placing this perspective in a sociolinguistic context and taking language use rather than form as the starting point for analysis, it is…

Until recently, professionals in the humanities have had access only to mainframe computer technology. The advent of microcomputers offers a range of new options. The experiences of one individual indicate that with personal computer technology and simple programming, and occasionally the help of a mainframe, textual, visual, and auditory…

A broad range of well-structured problems--embracing forms of diagnosis, catalog selection, and skeletal planning--are solved in expert computer systems by the method of heuristic classification. These programs have a characteristic inference structure that systematically relates data to a pre-enumerated set of solutions by abstraction, heuristic…

This manual outlines a coding system for the categorization of social action performed in talking, in the context of mother-infant interaction. The system, constructed for investigating the acquisition of language for social-communicative purposes, codes talk on two levels: the single utterance, and the interchange. Both kinds of units are defined…