AUTOMATIC INDEXING OF AUDIO-TEXTUAL DOCUMENTS BASED ON THEIR DIFFICULTY OF UNDERSTANDING

摘要

The server (SD) automatically indexes audio-textual digital documents (DAT) and audiovisual documents in particular by a comprehensibility difficulty index (IDC) of each document determined according to at least one index (IVE) resulting from a comparison of the speaking speed of the document evaluated at at least one threshold. The comprehensibility difficulty index may also depend on the numbers (nbFG) of predetermined grammatical forms included in each document as well as on a vocabulary index (IVC) determined in relation to predetermined lexicons. Each document is thus associated with a label gathering all the clues of it in order to allow in particular pupils or teachers of a foreign language in front of their terminals (TE) to search for documents in a base (DBMS) according to their understanding and knowledge of the language of the documents.