Ivan Kopeček

Hybrid Approach to Sonification of Color Images

This paper deals with the accessibility of graphics for visually impaired people. It presents a novel method of sonification of complex graphical objects, such as color photographs, based on a hybrid approach combining sound and speech communication. This approach is supported by a special color model, called semantic color model, which is introduced in the paper. The semantic color model possesses suitable properties that can be used to deliver the relevant graphical information in sound or speech in a convenient form. The integration of this approach with the annotated SVG format developed within the ongoing GATE project, which is also briefly described in the paper, enhances the efficiency of the system.

GATE to Accessibility of Computer Graphics

This paper presents a framework for integrating current information technologies into a platform enabling the blind and visually impaired people to access computer graphics based on the annotated SVG format. We also present a technique enabling the conversion of any graphical object to the annotated SVG format and easy annotation supported by OWL based ontology. This approach is not limited to vector graphics only, but enables also the flexible annotation and application of raster graphics (e.g. photographs). We briefly describe the architecture of the GATE (Graphics Accessible To Everyone) project, which contains the corresponding implemented modules. As an illustration, we provide an example showing how the blind can access the annotated graphics.

Modeling of the Information Retrieval Dialogue Systems

Formal models of dialogue systems and related notions (dialogue, dialogue strategy, evaluation function, dialogue communication, goal of dialogue) are introduced in the paper. A model of the information retrieval dialogue systems based on the dialogue strategies described by the Mealy-type automata and information systems (in the sense of Pawlak) is introduced and discussed.

Web pages for blind people — generating web-based presentations by means of dialogue

This paper deals with the problem of generating web pages by means of dialogue. The generated web presentations fully meet accessibility requirements. The basic approach is described and discussed. An illustrative example is presented as well

Very Low Bit Rate Speech Coding: Comparison of Data-Driven Units with Syllable Segments

Very low bit-rate (VLBR) coding of speech offers the opportunity to test methods of automatic generation of sub-word units. This paper describes two approaches to VLBR coding: the first based on ALISP (Automatic Language Independent Speech Processing) techniques, the second based on syllable segments. Experimental results are reported on a database of one Czech professional speaker. The obtained rates for unit encoding were approximately 135 bps for the former approach and 62 bps for the latter. The quality was evaluated by measuring the logarithmic spectral distortion (computed on LPC-spectra), and in informal listening tests. Possible mutual profits of each technique to the other are discussed.

Speech Recognition and Syllable Segments

Speech recognition based on the syllable segment is discussed in the paper. Special emphasis is put on the methods for estimation of syllable boundaries and methods of comparison of syllable segments by DTW algorithms. The method of characteristic function for estimating of the boundaries between syllable segments is introduced. This method is also utilized in the proposed DTW algorithm for syllable segments.

Creating pictures by dialogue

This paper deals with the problem of generating a picture of a scene by means of describing it in the terms of natural language ontologies. The corresponding graphical format, being formally represented in the form of the Pawlak information system, involves a full semantic description of the picture. Therefore, the pictures generated in this way “blind-friendly”, i.e. they can be automatically fully described. A simple example of such a picture generation is presented here

Adapting web-based educational systems for the visually impaired

Some problems related to adapting web-based educational systems to speech form are discussed in this paper. The approach is based on the conversion of HTML to VoiceXML. A characterisation of optimal menu trees for speech-based dialogue systems is presented. Experiments illustrating the effect of the minimality of menu trees are presented as well.

Algebraic Models of Speech Segment Databases

The paper deals with the problem of choosing and optimizing the inventories of speech segments (especially with respect to the concatenative speech synthesis). We offer taxonomy of the segment databases based on elementary properties of the segments in relation to a basic speech corpus. Next, we deal with a general abstract formulation of the problem and briefly discuss its algorithmic solution and applications.

Active and Passive Strategies in Dialogue Program Generation

An application of dialogue systems for developing computer programs is described and discussed in this paper. The concept of generating program source code by means of a dialogue involves combining strategies with system and user initiative. The strategy with system initiative safely navigates the user, whereas the strategy with user initiative enables a quick and effective creation of the desired constructions of the source code and collaboration with the system using obtained knowledge to increase the effectiveness of the dialogue. The described system, which was initially developed for visually impaired users, can also be used by novice programmers as a tool for learning programming languages.