Laurea degree in Electronic Engineering from the University of Padua in 1998. After finishing university I was engaged by ITC-irst as Consultant and, in 1999, as Researcher, working for the project DITELO (DIalogue on TELephOne), SSI division (Interactive Sensory Systems).

In the past, I developed spoken dialogue prototypes for telephone applications using ITC-irst speech recognition and dialogue technologies.
In July 1999, I attended MiLaSS (Multimodality In Language And Speech Systems, 7^th European Summer School on Language and Speech Communication), which was held at the KTH campus in Stockholm.
Also I developed the SPINET API (SPeech Into Enriched Text Application Programming Interface) in Java™ programming language. SPINET API has been inspired from the JSAPI (Java™ Speech API). Moreover I developed an interpreter in Java™ for our proprietary dialogue language, this language has been designed for creating audio dialogues using our technology.
I have started and partially completed a VoiceXML interpreter in Java™ (see VoiceXML forum). The interpreter can handle dialogues using mixed initiative strategy, where both the computer and the human direct the conversation.
A multi-modal browsing system is developed using the VoiceXML Interpreter, the idea is to synchronize different documents through a specific platform.
This approach has the advantage of allowing, in a quite general way, multi-modal browsing of existing HTML documents by developing corresponding VoiceXML documents.
In the course of 2002, I was an International Fellow in SRI (Stanford Research Institute, Menlo Park - California - USA), STAR Laboratory (Speech Technology and Research).

At present, I am involved in the following topics: spoken query retrieval through an adaptive dialogue management (spoken queries are used to retrieve relevant textural information) and acoustic modeling for automatic speech recognition.


My research interests mainly include: