An empirical study on voice-enabled web applications

A self-service voice-enabled Web system has been developed which integrates multiple interfaces to evaluate pervasive computing and provides users with choices for assessing information on the Internet. The speech recognition advances provide efficient voice capture and indexing mechanisms to make application systems with voice interfaces. A voice server has been used to enable the creation of voice applications using industry standards XML, VoiceXML, and Java. XML facilities application integration and data sharing and enables the exchange of self-describing information elements between nodes. The proposed system will create and transform XML-based data into two different types of information which includes information in various data formats that HTTP servers support and VoiceXML speech. The voice-enabled Web system has two user interfaces which include two dimensional Web browser interface and a one dimensional linear voice channel.