his project has result in the development of a prototype of Mobile App that allows the user, typically blind or visually impaired, to browse the web independently using voice controls. The mechanism used by the software works as an automatic syntactic extractor of web content. This extractor works with any websites built with markup language (HTLM5, HTML4, XHTML) and it is more efficient when the websites comply with the W3C-WAI(Web Accessibility Initiative) reccomandations.

The project idea is based on different common considerations to our country and to the rest of Europe.

The first is of a general nature and is based on the value of cultural tourism in Europe and in Italy. At a European level, and especially at an Italian level, the income generated by cultural tourism exceeds 335 billion Euros per year and plays a very important role in the tourism industry. Around 9 million jobs are connected to the Cultural Heritage while the conservation area market is estimated to be around 5 billion Euro (http://goo.gl/IV8qYc). In Italy, the available data shows that 36% of the total amount of incoming visitors, choose the cities of art, while cultural heritage and art are reasons for travelling for over 60% of the tourists (http://www.ontit.it).

The second consideration has to do with the crucial importance of this sector to the local economy and with the great changes the tourist is going through. The tourist has in fact became a highly evolved consumer, independent from intermediaries, able to organize his own holiday, looking for personalized services and more oriented towards short stays. This evolution leads also to a strong diversification of travel types, with the creation of new vertical market niches (fine dining and drinking destinations, eco tourism, etc.) and frequent combinations among these different tourism types.

A third consideration relates to the complex difficulties in preserving the Cultural Heritage. Countries are called to be responsible and protect their patrimony. This duty has been combined with the effort of creating balanced managing systems able to enhance the potential that these resources can offer from a point of view of economic growth and competitivity of territories, without ceasing to protect them.

It ‘s a three years project valued at 7,6 million Euros where Mediavoice leads 13 other companies, among them HP Italy, Loquendo, University of Rome and Palermo, Fondazione Bordoni and CNR. It is based on a new device engineered by Mediavoice called Mouse Acutattile. Already patented in Italy, it is now waiting to be patented internationally.

his project has result in the development of a prototype of Mobile App that allows the user, typically blind or visually impaired, to browse the web independently using voice controls. The mechanism used by the software works as an automatic syntactic extractor of web content. This extractor works with any websites built with markup language (HTLM5, HTML4, XHTML) and it is more efficient when the websites comply with the W3C-WAI(Web Accessibility Initiative) reccomandations.

All’interno di questo progetto si realizza il prodotto Speaky PC Facile del futuro. È un progetto che realizza il prototipo di architettura ed il meccanismo di fruizione di risorse vocali TTS (Text To Speech) e ASR (Automatic Speech Recognition) in ambienti Virtualizzati. Grazie alla virtualizzazione delle risorse hardware e software, al cloud computing e all’aggiunta della tecnologia vocale a questi due mondi, sarà possibile disporre lato server di sistemi che contengono tutta la logica applicativa in remoto e abilitano un terminale stupido, quindi estremamente economico, lato client. Tale terminale effettuerà la semplice funzione di accesso la servizio che è realizzato, accresciuto e manutenuto lato server. Lo Speaky PC Facile di dopodomani quindi, non è più un hardware con un software a bordo, sarà bensì un servizio (Software As a Service), che a non vedenti e ipovedenti (e non solo) sarà distribuito al costo di un ‘ridotto’ canone mensile. In casa l’utente avrà solo un terminale stupido che non ha bisogno di essere mantenuto e aggiornato, sarà tutto lato server, con in più la peculiarità di supportare il riconoscimento e sintesi vocale virtualizzati, con architettura basata su brevetto pending. Il progetto terminerà a fine 2012, il prototipo sarà industrializzato da un’azienda partner (Ingegneria 2000) e messo sul mercato insieme nel 2014

This project aims to create a voice interface for a story telling system in the Cultural Heritage field.

EDI is a new inclusive platform for digital publishing enhanced by voice interaction and virtualization. The project consists of the production of a series of innovative instruments for digital publishing accessibile through different hardware and software systems both for Desktop and Mobile.

SPEAKY for Robots (S4R) aims at fostering the definition and deployment of voice user interfaces (VUIs) in robotic applications where human-robot interaction is required. S4R promotes speech technologies transfer towards manufacturing processes, to provide semi-automatic speech-based interface development for robotic platforms. This in turn will boost up the robot presence in manifold activities, by supporting a natural interaction with humans. S4R’s specific goal is a novel Robotic Voice Development Kit (RVDK). A RVDK is conceived as an interactive environment aiding designers to define the voice interface according to the desired application requirements. In order to design and implement the RVDK, state of the art solutions about lexical vocabularies and knowledge representation to capture the semantics of the domain, and natural language processing technologies will be integrated. S4R targets two possible application domains: Home services, where a user controls a humanoid robot through a voice user interface, and outdoor robotic surveillance, where the user is controlling the action of a wheeled robot capable of navigating in rough terrain.

Speaky for Robot, sviluppato con Uniroma1, ha permesso la definizione e lo sviluppo di nuove interfacce vocali UOMO-MACCHINA specifiche per applicazioni robotiche. Nell’ambito di questo progetto è stato realizzato un innovativo kit di sviluppo robotico (RVDK – Robot Voice Developr Kit), che supporta gli sviluppatori nella progettazione di interfacce utente vocali per i Robot. L’RVDK è stato concepito come un ambiente di sviluppo che permette ai progettisti di definire le interfacce vocali in base ai requisiti applicativi desiderati; quindi, è adattabile a diversi campi di applicazione. Le interfacce prodotte dall’ RVDK sono integrate automaticamente nella piattaforma Speaky per l’interazione via voce tra utente e Robot nel dominio per cui sono state progettate.