Development of an online subjective evaluation system for recorded speech of deaf and hard of hearing children

Abstract

The aim of this paper is to present a web-based evaluation system developed as part of a research has been carried out in cooperation with University of Debrecen and University of Miskolc in the framework of the project TÁMOP-4.2.2.C-11/1/KONV (Social Renewal Operational Programme) called `Basic and Applied Research for Internet-based Speech Development of Deaf and Hard of Hearing People and for Objective Measurement of Their Progress'. The project is aimed at solving basic and applied research tasks to develop an application to support the speech teaching and understanding of deaf and hearing-impaired people more effectively than known methods. The idea of the project has come from an audio-visual transcoder for sound visualization developed at the University of Debrecen, and a three-dimensional head model for articulation presentation, called `talking head' developed at the University of Miskolc. The most important aim of the project is to create a complex system to provide audio-visual speech recognition by visualization of images of speech and articulation, setting up an educational framework. In addition, the system has many other features (prosody display, automatic evaluation and knowledge-based systems implementation), which subsequently allow individual practice not only on computers but also on mobile devices. However, it is important to note that personal contribution of surdo-pedagogues can not be replaced, but can greatly support. The module performing the required audio-visual transcoding is language-independent, the talking head, moreover automatic qualification can be made language-independent by training new neural networks. For development of automatic qualification, the recorded speech samples has been required to be evaluated by surdo-pedagogues and lay students. The online evaluation system developed for this purpose is shown in this paper.