The M-PIRO project targets the concept of personalized information objects ─ that is, entities capable of responding to requests for information by taking into account what the requester already knows, what they are most interested in, and how the related information is to be made available. M- PIRO's technology allows textual and spoken descriptions of exhibits to be generated automatically from an underlying language-neutral database, existing free-text descriptions, or a mixture of the two. The resulting descriptions, produced in three different languages (English, Greek, and Italian), are tailored according to the user's interests, background knowledge, and language skills. Particular research emphasis is placed on user modeling for personalization and authoring tools that allow museum caretakers to create on-line and virtual presentations of exhibits. Improvement of the synthetic speech output quality has been achieved via a closer integration between text generation and speech synthesis, and by using domain- specific trained prosodic models.
Calder, J., Melengoglou, A. C., Callaway, C., Not, E., Pianesi, F., Androutsopoulos, I., … Roussou, M. (2005). Multimodal Intelligent Information Presentation. (O. Stock & M. Zancanaro, Eds.) (Vol. 27, pp. 177–201). Dordrecht: Springer Netherlands. https://doi.org/10.1007/1-4020-3051-7