Rehabilitation of Dyslexics Using Language Technology and Multimodal Techniques

Reading and writing at a level that is close to the general reader in a society can by no means be taken for granted - not even in countries where the educational level is high. Dyslexia is one of a number of known language disorders that affects these skills and thus affects a person?s daily life communication skills. Dyslexia literally affects millions of citizens all over the world. As functioning in the modern society increasingly relies on the written medium as mean of communication (e.g. by utilising the Internet) this constitutes a problem of increasing magnitude. This further underlines the need for establishing new and improved methods for teaching and helping dyslexic persons aimed at their integration into the modern society. So far much effort in providing teaching of the dyslexic part of the population has to a large extent demanded involvement of long-time assistance from professional therapists. Sheer lack of available personnel and limited public financial resources however means that new ways have to be established for the future rehabilitation of the dyslectic part of the population.   Multimodal and language technological elements are today being used in assistive tools for people with language disorders. Despite the fact however, that language technology in terms of e.g. speech recognition and synthetic speech in the past years has undergone significant improvement, and new technological possibilities thereby have emerged, little research has been placed in the area of successful of language technology into multimodal communicative aids. Language technology has so far mostly been used as an of-the-shelf solution in combination with existing multimodal aids, this way not unleashing the full potential of this integration. integration The focus in this Ph.D. project initiated September 2003 is placed on research within the field of methods and techniques for computer assisted rehabilitation of dyslexics. The potential of successful integration of current state-of-the-art speech and spoken language technology (i.e. speech recognition and synthetic speech) assisted with multimodal presentation schemes will be researched and analysed, and will constitute the innovative component of the research.     The project will comprise a high degree of multidisciplinary research, bringing together knowledge and expertise from areas that traditionally belong to the humanities (e.g. health and education), language processing and intelligent multimedia.