A Design of User-Initiative Voice Web Using RSS and VoiceXML

Abstract

A voice web accesses web resources via voice and audio. VoiceXML is currently the best solution for construction of a voice web. However voice web using VoiceXML doesn 't provide users with dynamic and rich content because a voice web uses machine- controlled and mixed-initiative technology that provides one-sided progress from system to user. In this paper, we recognize the weaknesses of a voice web using technology such as VoiceXML, and design and implement a user-initiative voice web using RSS and VoiceXML. The proposed system provides dynamically detected recognition candidates in user content, in contrast with recognition candidates of the existing voice web, which depend on the application developer. As a result of implementation and experiments with the proposed system, we confirm that users can navigate more freely and efficiently.