An Implementation of Intelligent HTMLtoVoiceXML Conversion Agent

摘要

This paper is a presentation of a new intelligent agent that is able to convert HTML contents to VXML contents to provide voice services for text disabilities via web. Prior to interpreting HTML documents and separating contents, the contents for the conversion must be selected, however, there are no good solutions for selecting the desired group contents. In this paper, I propose an interactive hybrid sequential contents selection method to select desired contents fast and robustly from known web pages. It uses real time structural features as well as included text and/or prior structural knowledge such as link, symbol and position. To verify its effectiveness, a full agent system is implemented and tested for Korean web sites. In the result of applying this method to 200 web pages, the separation successful rate was 100% except for the pages that described the wrong HTML grammar. The method reflects the user's intention more accurately than conventional selections using structural features and is more robust to variations of HTML programming techniques. The agent is fast and has less of a computational burden than methods using conventional XML or XHTML conversion as an intermediate stage.