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.…

The paper describes dynamic orometric instrumentation and procedures developed to measure, display, and guide changes in vowel and consonant production through visual articulatory modeling and feedback routines. Sensors are placed in the mouth to detect tongue shapes, positions, and actions during speech of hearing-impaired talkers, and online…