The DICIT project is introduced, presenting major goals and the applicative scenarios (interactive TV and home surveillance). A general overview of the architecture is given; the involved technologies comprise acoustic echo cancellation, distant-talking speech recognition, advanced natural language understanding and dialogue management. In particular, issues related to the understanding system and the design of the dialogue are analyzed. A discussion about envisaged metrics for on-field performance evaluation concludes the paper.
The DICIT project: an example of distant-talking based spoken dialoque interactive system
Matassoni, Marco;Omologo, Maurizio;
2008-01-01
Abstract
The DICIT project is introduced, presenting major goals and the applicative scenarios (interactive TV and home surveillance). A general overview of the architecture is given; the involved technologies comprise acoustic echo cancellation, distant-talking speech recognition, advanced natural language understanding and dialogue management. In particular, issues related to the understanding system and the design of the dialogue are analyzed. A discussion about envisaged metrics for on-field performance evaluation concludes the paper.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
