STiLL - Speech Technology in Language Learning

May 25-27, 1998
Marholmen, Sweden

Prosodic Modeling for Automatic Language Tutors

Rodolfo Delmonte

Universita Ca' Foscari - Ca' Garzoni-Moro, Laboratorio Linguistico Computazionale, San Marco, Venezia, Italy

We present the Prosodic Module of a courseware for computer-assisted foreign language learning called SLIM - an acronym for Multimedia Interactive Linguistic Software, developed at the University of Venice( see [1], [2]). The Prosodic Module has been created in order to deal with the problem of improving a student's performance both in the perception and production of prosodic aspects of spoken language. It is composed of two different sets of Learning Activities, the first one dealing with phonetic and prosodic problems at word internal level, the second one dealing with prosodic problems at phonological phrase and utterance level. Word-internal refers to syllable-sized segments. As to phone-sized segments, they are practiced in a separate Module where speech recognition is used. The main goal of Prosodic Activities is to ensure feedback to the student intending to improve his/her pronunciation in a foreign language.

References

  1. Delmonte R., Dan Cristea, Mirela Petrea, Ciprian Bacalu, Francesco Stiffoni (1995). Modelli Fonetici e Prosodici per SLIM, Convegno GFS-A1A, Roma, 47-58.
  2. Delmonte R., Andrea Cacco, Luisella Romeo, Monica Dan, Max Mangilli-Climpson, Francesco Stiffoni (1996). SLIM - A Model for Automatic Tutoring of Language Skills, Ed-Media 96, AACE, Boston, 326-333.

Full Paper

Bibliographic reference.  Delmonte, Rodolfo (1998): "Prosodic modeling for automatic language tutors", In STiLL-1998, 57-60.