The first prototype of the H2020 European Project KRISTINA was presented in
November 2016 in Tübingen (Germany) as a virtual agent, able to talk and
interact with users in controlled conditions. The first European virtual
assistant in the field of healthcare understands and speaks Spanish, German
and Polish, and has a proper voice and aspect.
The goal of the KRISTINA project is to develop technological solutions to help
overcoming migrants' language and cultural barriers in healthcare and geriatric
services in their host countries. With the first prototype, KRISTINA becomes a
conversation partner. Technical partners are constantly working in order to
ensure a natural interaction with the agent, improving its expressions and its
ability to recognize and interpret content, emotions and human feelings. The
first prototype has been successfully tested. It demonstrates the current
state-of-the-art in spoken dialogue interaction by means of a fully functional
integrated platform.
For the first prototype, Vocapia developed real-time speech-to-text solutions
adapted to the KRISTINA domain in Spanish, German and Polish. Extensive
development work has been carried out to improve accuracy by 10%
absolute in average since the beginning of the project. The novel real-time
systems can produce speech transcriptions with small latency delays (less
than 0.7 second in average).
At the present stage, KRISTINA is able to interact with users within
pre-defined scopes, responding to questions about health assistance, advising
on specific health issues or reading newspaper articles.
Research and development will continue to enable the agent to hold
conversations on a larger variety of topics, to provide responses at
real-time, to recognize emotions, face expressions and body gestures, as well
as to adapt itself to the user's cultural context. For the next prototypes,
support will be extended to Turkish and Arabic.
Vocapia's partners in KRISTINA are:
- Universitat Pompeu Fabra, Spain;
- Sociedad Española de Medicina de Familia y Comunitaria, Spain;
- Almende BV, Netherlands;
- Centre for Research and Technology Hellas, Greece;
- University of Augsburg, Germany;
- Universität Tübingen, Germany;
- Universität Ulm, Germany;
- Deutsches Rotes Kreuz, Kreisverband Tübingen, Germany.
Project website:
http://kristina-project.eu/en/
Twitter:
https://twitter.com/projectKRISTINA
Facebook:
https://www.facebook.com/projectKRISTINa
LinkedIn:
https://www.linkedin.com/groups/12003450
Vocapia Research, founded in July 2000, is an R&D company and
software publisher developing and providing leading edge speech
technologies and solutions for many languages, including most major
European Union languages as well as Arabic, Mandarin, and Russian. The
Vocapia Research VoxSigma
® software suite uses advanced
language technologies such as language identification, speech
recognition, and speaker identification to transform raw audio and
audiovisual data into structured and searchable XML documents. This
technology relies on over 25 years of research at LIMSI-CNRS, with
which there is a priviledged partnership. Joint systems developed
with LIMSI have achieved top ranks in national and international
challenges of speech-to-text transcription. The most common
applications of the VoxSigma software suite are audio and audiovisual
data mining (broadcast data, podcasts, call center data), media
monitoring, and media asset management. Vocapia Research is located in
the scientific pole of the Saclay Plateau, France. Readers who wish to
get more information about Vocapia Research are invited to check out
the Vocapia Research website or use the contact information page
http://www.vocapia.com/contact.
