FP6 - V Call

• LUNA (spoken Language UNderstanding in multilinguAl communication systems).The main objective of the LUNA project is the creation of a robust natural spoken language understanding (SLU) toolkit for multilingual dialogue services, able to carry on human-computer communication with a good degree of user satisfaction.
  From a technological point of view, LUNA's objectives include the investigation of new methods, algorithms and tools for the fast development of robust SLU components for multilingual telecom services. To this aim, LUNA will address a set of challenging scientific problems, by focusing on five scientific objectives:
  
  - Language Modelling for Speech Understanding
  - Semantic Modelling for Speech Understanding
  - Automatic Learning (including Active and On-Line Learning)
  - Robustness issues for SLU
  - Multilingual portability of SLU components
  
  The SLU models will be trained and applied to different multilingual spoken dialog systems in French, Italian and Polish.
  LUNA's research results will be validated on different application scenarios, targeted to dialogue-based telecom services of different complexity (e.g. from call routing with utterance classification to dialogue systems with complex semantic domains).
  

• C@R (Collaboration@Rural: a collaborative platform for working and living in rural areas) IP project aims to boost the introduction of Collaborative Working Environments (CWE) as key enablers catalyzing rural development. According to this strategic goal, the C@R Integrated Project proposes a complete set of research activities and tasks which will identify, develop and validate technological responses to actual barriers jeopardizing the sustainable development in rural areas.

  To achieve this priority objective, C@R will advance on the specification, development, test and validation of a powerful and flexible worker-centric collaborative platform that will significantly enhance the capabilities of rural inhabitants, both, @work and @life, thus leading to a better quality of life and a revalorisation of rural settings.

  From the technical standpoint, C@R will organise the work in three layers:

  - Rural Living Labs
  - Software Collaborative Tools
  - Collaborative Core Services

  The consortium includes partners from Spain, Greece, Finland, Germany, Austria, France, Belgium, United Kingdom, Israel, Hungary, Czech Republic, Poland, China, Brazil, Italy.

• COMPANIONS (Intelligent, Persistent, Personalised Multimodal Interfaces to the Internet) is an IP project which aims at making ECAs (Embodied Conversational Agents) a reality by developing the next generation of technologies for them. As an Integrated Project, COMPANIONS will advance the state-of-the-art of key enabling technologies, and it will offer a new perspective on the integration of ECA as interface systems, which will ultimately translate into better software architectures for industrial transfer and application deployment.
  
  COMPANIONS relies on a rich background of human languages technologies developed by its partners, such as dialogue technologies and high quality text-to-speech. An emphasis within COMPANIONS is to rely heavily on machine learning techniques to relieve the traditional bottleneck of language technologies.
  The COMPANIONS project will provide:
  
  - A set of COMPANION interfaces, which will consist of ECAs supporting multimodal dialogue. These will be personal and persistent, supporting not only traditional information access but also personal data and knowledge organization;
  - An overall development methodology for multimodal ECAs;
  - A new paradigm for multimodal architectures, which will depart from overly complex software engineering approaches and will relay on adaptive architectures based on machine learning techniques;
  - COMPANION interfaces displaying multi-lingual and cross lingual capacity.

  The consortium is composed by partners from United Kingdom, Czech Republic, Sweden, USA, Finland, France, Spain and Italy.
  

FP6 - IV Call

• I-WAY (Intelligent co-operative system in cars for road safety). The goal of I-WAY is to develop a multi-sensorial system that can ubiquitously monitor and recognize the psychological condition of driver as well as special conditions prevailing in the road environment.
  
  The I-WAY platform targets mainly road users, but it is a highly modular system that can be easily adapted or break up in stand alone modules in order to accommodate a wide variety of applications and services in several fields of transport, thanks to its interoperability and scalable system architecture.

FP6 - II Call

• SHARE (Mobile support for rescue forces, integrating multiple modes of interaction).The highly challenging SHARE project will develop a Push-To-Share advanced mobile service providing multimodal communication support for emergency teams during critical rescue operations.
  Specific innovations will be developed by the SHARE project including mobile system architecture design to enable bi-directional multimodal communication using Push-To-Share technology, robust speech (TTS, Text-To-Speech and ASR, Automatic Speech Recognition) and image processing under extreme conditions, interactive digital maps with linked multimedia information and structuring of required information using situation-dependent ontologies and multimedia data indexing capabilities
  The SHARE concept will be integrated into a mobile communication infrastructure based on 2.5G, 3G (UMTS) and mobile WLAN networks.
  The project involves partners in Germany, France, Belgium, Greece and Italy, as some of the major Telco operators, R&D institutes and Universities.
  To better cope with, and to be compliant with the real technological and functional requirements of such a solution, the involvement of final users within the project framework has been granted.

• SNOW (Services for NOmadic Workers). The SNOW project will rely on existing or emerging telecommunication infrastructures for bolstering on the field new maintenance services that will deliver key competitive advantages to European manufacturing industries: direct access to maintenance documentation on various and sometimes difficult work situations, in situ report of operations, expertise projection, cross team communication and remote access to knowledge databases.
  The main objectives of SNOW are to solve two main hurdles that prevent from a large scale industrial diffusion of multimodal mobile documentation for maintenance operations:
  - How to author multimodal mobile maintenance documentation
  - How to exploit this documentation through robust interaction modalities
  Main objectives will be to offer full multimodal support from documentation authoring to exploitation as well as corresponding environments, to define an XML based language for representing device independent multimodal documentation and a common standard-based user interface integration format for exploitation on mobile devices; to develop a maintenance application for validating these technologies and assed with usability tests based on real business scenarios.
  The project, lead by the largest European aerospace company renown for the excellence of its maintenance processes involves key European players for document management, voice technologies, vision and gesture recognition and integration of multimodal presentation.
  Partner involved countries are France, Germany, Austria and Italy.
  The project has been completed in September 2006

FP6 - I Call

• DIVINES (Diagnostic and Intrinsic Variabilities in Natural Speech). The ultimate goal of DIVINES is to provide alternatives to the current state-of-the-art feature extraction, acoustic modelling and lexical modelling techniques, and to contribute to the long-term goal of bridging the gap between human and machine speech recognition performance. DIVINES will particularly target techniques that will have better capacity in handling speech intrinsic variabilities and non-stationarity. At least two ways to cope with the variabilites will be investigated.
  First, detecting them will allow to use more appropriate models (both acoustic and lexical) to improve voice recognition. Second, accurate characterization will allow to design more robust or adaptable features and models and hence improve the recognition accuracy.
  The project involves main European research centres, Universities departments and enterprises from Belgium, France, Germany and Italy, leading voice technology R&D.
  The project has been completed in January 2007

• HIWIRE (Human Input That Works In Real Environments). The HIWIRE project aims to make significant improvements to the robustness, naturalness, and flexibility of vocal interaction between humans and 'machines'.
  The industrial partners involved in the project (from France, Greece, Italy and Spain) expect that the technological breakthrough targeted in this project will deeply impact their future activities by:
  - enabling the introduction of vocal dialogue with equipment in commercial aircraft cockpits;
  - improving the potential for vocal interaction with PDAs and other mobile devices in aeronautic application environments.
  The HIWIRE project will go well beyond the current state-of-the-art for robust vocal dialogue involving large flexible vocabularies, by focusing on two main targets: improved robustness against the environment (mostly unpredictable noises like those encountered in cockpits with dense audio traffic or factory noise…) and improved tolerance to user behaviour (including speakers' vocal individuality, different accents, non-native speech, dialogue skills…).

• HOPS (Enabling an Intelligent Natural Language Based Hub for the Deployment of Advanced Semantically Enriched Multi-channel Mass-scale Online Public Services). HOPS is a three-year project focused on the deployment of advanced ICT "voice-enabled front-end public platforms" in Europe permitting access for European citizens to their nearest Public Administration.
  
  The main objective is to address the mass-scale deployment of new online public services supported and accessible by voice channels (basically phone, both fixed and mobile), the most accessible and communication means used by European Citizens. This will only be possible by the addition of new fully functional advanced technologies enabling to deliver automated services without losing any quality and even more enhancing the current functionalities even more.
  
  In this respect, the project is based on the integration of voice technologies (VoiceXML - ASR, Automatic Speech Recognition - TTS, Text to Speech) with Natural Language Processing technologies, complemented by a Public Administration sector-specific implementation of Semantic Web Technologies. The overall approach follows a systemic structure, aimed to produce fully functional prototypes, which will be tested and validated by the three Local Authorities involved in the project.
  
  The project is a collaborative effort of: Municipality of Barcelona, Spain; Municipality of Turin, Italy; London Borough of Camden, UK, and other industrial partners.
  
  The HOPS project's working basis is that the joint effort of some of the most advanced Local Public Authorities, R&D companies and organisations, and systems integrators will lead to deploy and implement an advanced ICT-enabled platform aimed at integrating an intelligent natural-language based multi-channel front-end with the knowledge repository of local Public Administration.

FP5

• SMADA (Speech Driven Multi-modal Automatic Directory Assistance).
  The project has developed the technology to handle a substantial proportion of the calls from both fixed and mobile networks automatically, by improving the efficiency and effectiveness of human language technologies embedded in automated telephone and web-based directory assistance services.
  Besides the aspect related to significant cost advantages that these technologies offer, within the project framework their impact on customer satisfaction and the customer perceptions of service quality have been assessed.
  The project has been completed at the end of 2002.

• SPOTLIGHT (Mass Market E-commerce Services using Multi-language Natural Spoken Dialogues).
  SPOTLIGHT has been a three-year project (2000- 2002) that involved major players in the financial services and travel industries sectors in Germany, the UK and Italy, supported by technology providers for these three languages (German, English and Italian).
  It has aimed to extend the spoken natural language and speech recognition capabilities of financial services and travel industries and to push the technology boundaries of telephone-based spoken natural language user interface capabilities beyond the usual limits of information provision, to offer users a friendly interface that matches their individual needs.
  In this context, Loquendo has developed and experimented two services for over-the-phone access to personal tax information held by the City of Rome Tax Office's TARSU (Tassa per lo smaltimento dei Rifiuti Solidi Urbani) and ICI (Imposta Comunale sugli Immobili) divisions.
  The project has been completed at the end of 2002.

• PANDORA (Pilot Action oN Digital economy Opportunities for Rural Areas)is a high-impact project designed to show the concrete development opportunities for regional economies brought by R&D activities conducted for the creation of an innovative multimodal, multichannel, multimedia mobile (3G, WLAN) platform able to usefully employ voice technologies (Text-to-Speech and Automatic Speech Recognition) for regional public services (administration-to-citizen, administration-to-business and administration-to-administration).
  The project involves partners from Italy, Ireland, Greece and Bulgaria as Regional Governments from and outside the Union, large Mobile Telecommunication Operators, renowned Research Centres and leading-edge medium-sized IST Providers, ideally well positioned to address this opportunity.
  The project has been completed at the end of 2004.