Speaky Internet

Project objectives

The main objective is to develop Artificial Intelligence (AI) methodologies, possibly based on Deep Learning (DL), for the syntactic/semantic/morphological extraction of information from web pages, then proceeding to the classification and organization of the content also through the study of multimodal learning methods. Thanks to this extraction, in a subsequent phase of the project the menus and contents identified in the web pages will then be filtered and ordered based on the semantic relevance of the end user's preferences, to then be presented to the user using a speech synthesizer according to various priority criteria, realizing an effective and simple user voice interaction and creating an intelligent real-time dialogue flow.

This will lead to:

• The development of learning models for the syntactic, semantic and morphological extraction of web pages;
• Development of multimodal learning models to integrate the heterogeneous information extracted in the previous point, to reach the final classification of the page content.

Start and end date

Project Manager

Coordinating institution of the project

Other Institutions involved

Funding source(s).