Appl Intell (2006) 24: 253–261 DOI 10.1007/s10489-006-8516-5 Architecture and dialogue design for a voice operated information system Luis Villarejo · Javier Hernando · N´ uria Castell · Jaume Padrell · Alberto Abad C  Springer Science + Business Media, LLC 2006 Abstract In this paper we present a real automatic meteo- rological information system that, not only provides friendly voice access to real-time data coming from automatic sen- sors, but also establishes an automatic warning service on the weather. It aims to extend the availability, personalization and friendliness of the meteorological information by means of a reusable easy-to-use friendly oral natural language interface. This interface takes advantage of the improvements in speech processing, dialogue handling and the great growth of mobile telephony. After the description of the functionalities of the system and its architecture, we present in detail the features of the dialogue manager. The main goals we have considered are: to provide the right information and to design a friendly interface. Keywords Intelligent interfaces . Natural language processing . Speech processing and VoiceXML 1. Introduction Meteorological information has long been provided by tele- vision and radio as weather reports scheduled at a fixed timetable giving impersonal information. Nowadays there are telephonic systems that offer some personalized infor- mation but in an unnatural way. Usually these systems offer some menus operated via the telephone keyboard and have a very limited vocabulary. These features condemn the sys- tem to failure in the real world due to a lack of naturalness and fluency in the dialogue. This kind of systems usually L. Villarejo () · J. Hernando · N. Castell · J. Padrell · A. Abad TALP Research Center, Universitat Polit` ecnica de Catalunya Campus Nord - A0, Jordi Girona 1-3, 08034 Barcelona, Spain e-mail: {luisv, javier, castell, jaume, alberto}@talp.upc.es provide general information and are updated less frequently than desired. The interest and research on interactive speech systems has increased in recent years due to the extended use of tele- phone information systems. We should mention the TRINDI [1] (Task-Oriented Instructional Dialogue) project, which fo- cuses in generic technology for the creation of a dialogue movement engine. Nowadays there are systems that offer a good level of interaction during the information exchange. Some examples are the following: ARISE [2] (Automatic Railway Information Systems for Europe), TRAINS [3], and BASURDE [4] (Spontaneous Speech Dialogue System in a Semantically Restricted Domain), all of them are about railway information, and ATIS [5] (Air Travel Information System), is about flights. Some systems are designed to offer meteorological information in a user-friendly way. A refer- ence work in this field is the JUPITER [6] project. The system described here provides personalized real- time data, in the Catalan language, on a set of meteorological conditions on each place of the Catalan geography through an easy-to-use natural language interface. It also provides an alarm and warning system, based on the same interface, that keeps the user informed on the variables of his/her interest whenever they occur. The whole system has been constructed on the basis of VoiceXML (the voice standard promoted by the World Wide Web Consortium), specifically the voice framework and the dialogue manager. The VoiceXML standard [7] is taking an important role in giving support to this kind of interactive speech systems de- velopments which cover a great range of domains. To quickly review some VoiceXML-based systems we should mention the INSPIRE [8] (Infotainment management with speech in- teraction via remote-microphones and telephone intefaces) project, which focuses on speech dialogue-based assistant for wireless command and control of home appliances. Also the Springer