Département Artemis

Linguistic Meta-Educational Engine for Audiovisual Content

LIMED develop an innovative demonstrator than can turn any available foreign language video (e.g., TV serials or evening news) into a terrific learning tool for the language in question.

Thus, the LIMED project is anchored in the new field of Edutainment (Education + Entertainment), proposing the automatic generation of comprehension quizzes on highly attractive preexisting audio-visual content (for example, foreign language TV series or news). This engine will be implemented for contents that can be accessed on the go, anywhere and at any time.

LIMED proposes a new interactive, individualized and motivating solution to learn a foreign language while watching and enjoying one’s favorite original language video on a mobile device or PC laptop.

The interactivity introduced by the quiz, combined with a scoring system as used in video games (instant results and results evolution) shall encourage regular practice. The user experience has to be perceived (especially by younger users) as entertainment, rather than education.

While maintaining a pragmatic and focused approach, targeting a measurable outcome, the automatic quiz service, LIMED innovation is twofold. First it brings together areas of expertise that rarely work in common  (language learning methods and multimedia characterization) and second it targets a web-based, open multimedia description system covering both low-level descriptions and high level ontology.

Beyond the usual forms of interactivity (e.g. video/multimedia games, video inserts, etc.) this project is paving the way to a whole new form of interactivity. The LIMED engine will generate a linguistic comprehension quiz for any video, turning one’s favorite TV programs into learning material.

With respect to language learning approaches, the innovation lies in the fact that the LIMED engine can be applied to pre-existing media content, i.e. content that is already known and compelling to the user, therefore strengthening the learning because a cognitive frame of reference already exists and an adoption pattern is fostered.

 Partners: 4n Media, Jamespot

 Project site: http://www.limed.org/

 Type: National

 Keywords: e-learning, compression, face reconition, MPEG-7

 Contact: Marius Preda