Abstract: This paper presents a proposal for the use of distributed speech technologies like Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) synthesis to create a paradigm of web development which integrates voice as input and output interface in the navigation experience. This enhanced usability is aimed to provide accessibility to the Internet for the community of blind and visually impaired people, whose access nowadays is difficult and costly. The novel concept in this work is to provide the web developer all the control on the use of the speech synthesis and recognition, i.e. designing the voice experience within the website through the use of a simple set of tags, rules and functions. A pilot experience with Aragon Radio 2, the online radio channel of the Aragonese Corporation of Radio and Television (CARTV), has shown the arising possibilities for this technology and opens the interest for further use of them in collaboration with different institutions.
Index Terms: visual impairments, technical aids, web accessibility, speech synthesis, speech recognition.