Journal of Microcomputer Applications最新文献

This paper reports the outcome of a project sponsored by the UK Government Training Enterprise and Education Directorate (TEED) to produce CAL material to teach employment-related language to hearing-impaired school leavers. The tutorial content was decided after conducting a survey of teachers of the deaf. A survey of the literature relating to language and the deaf produced a number of rules for the generation of the language content. The language used was also agreed with teachers of the deaf before implementation of the system. Tutorials were written at two levels of language so that the material can be related to the needs of the student using the system. These needs are assessed by a computerized version of the SPAR reading rest. A management system guides the student through the tutorials and reports back to the teacher on the student's progress, what help has been requested, and the results of the tests which are included in the tutorials. Because of the complexity of the system a rigorous methodology was required at the implementation stage. This is explained in the paper and results of the evaluation of the system, by pupils and teachers, are given.

A product-oriented teaching and training system has been developed for speech handicapped persons which helps to control their speech production by visual feedback. This method helps teachers to obtain better and quicker results. Futhermore, this interactive feedback system has a game-like strategy, which gives the patients a new motivation to practice alone. This speech therapy method is built up in four different steps: (1) sound preparation, (2) sound development, (3) practice in words, (4) practice in sentences (automation).

The method is mainly useful for patients who are hard of hearing or deaf, but serves for dyslalic cases too. With the help of a special processor the speech is analysed by an auditory model and visualizes it in an illustrative and playful way. The therapy program has been developed for use in several different cases of aetiological background (such as hearing problems, cleft palate, disorders of auditory perception, etc.), and for various languages. There is a set of modules in it for building dictionaries according to the language and/or the kind of the defective pronunciations. This paper presents both the general methodological steps and the results of the correction of sygmatism.

There is a considerable interest in designing automatic systems that can scan a given paper document and store it on electronic media for easier storage, manipulation and access. Most documents contain graphics and images, in addition to text. Thus, the document image has to be segmented to identify text and image regions, so that appropriate techniques may be applied to those regions. In this paper, we have presented a new technique for image segmentation in which text and image regions, in a given document image, are automatically identified. The technique is based on the differential-processing text extraction concept. The proposed technique is capable of analysing complex document image layouts. The document image is processed by using textural feature analysis. Results of the proposed method are presented with test images which demonstrate the robustness of the technique.

Some people have impairments which made their speech quite difficult for other people to understand. However, it may be that computers could be trained to reliably recognize their speech. This paper will present the results of a preliminary, small-scale experiment which produced encouraging results to support this proposition.

This project used the technique of Time Encoded Speech and was tested using a person with cerebral palsy. It showed a sufficiently high level of recognition to suggest that the technique could be applied, though it might be restricted to applications involving a limited vocabulary.