This paper is concerned with speech training systems which intend to show how to articulate vowels and some consonants displaying vocal tract shapes. The first one is implemented on a microcomputer and relates to articulation of vowels. It shows whether the uttered vowel is more similar to the intended vowel than to each of the other vowels, and instructs how to articulate the vowel by displaying both the reference lateral vocal tract shape and the one presumed from the uttered voice. It can adapt its performance automatically to the child's progress pace in learning. It can be used as a discriminator of words, and is also suitable for self-teaching. The other system estimates the vocal tract shapes of vowels and of some stop and fricative consonants from uttered speech waves, and instructs how to articulate. For the articulation of vowels, the system points out defects about the place of articulation and opening of lips, and for the articulation of consonants, it points out the defect about the place of articulation and displays how to correct the articulation.

A speech recognition system for continuously spoken Japanese sentences is described. The system has a knowledge source, in which syntactic, semantic and vocabulary knowledge are contained. It can treat not only simple sentences but also simple complex and compound sentences without any restriction regarding the tasks. Phoneme identification is performed in real time, and after a slight revision has been carried out the speech sound is represented by a pseudo-phoneme string. In the syntactic knowledge system, inflections of inflectional words are taken into account. The syntactic analyzer, using a syntactic state transition network, predicts the following words and outputs their syntactic interpretations. The semantic knowledge system deals with the meanings of each word, in particular, it deals with case structures for verbs. The semantic knowledge is used for the prediction of the following words and construction of a semantic network of the input story. Moreover, a slightly modified version can be used as a speech input device of a word processor.