Developing automatic speech recognition-enabled language learning applications: From theory to practice
03 / 2008 - 05 / 2014
The emergence of Computer Assisted Language Learning (CALL) systems using ASR offers new perspectives for training oral proficiency. In this research project, a prototype of an ASR-based CALL application for Dutch as a second language (DL2) will be developed. The application optimizes learning through interaction in realistic communication situations and provides intelligent feedback on important aspects of DL2 speaking: pronunciation, morphology, and syntax. To this goal, existing, improved and newly developed technology must be integrated. Some directions for research are ASR for non-native speech, utterance verification and error-detection for pronunciation, morphology and syntax. We will evaluate the system by carrying out four pilot experiments which are aimed at testing the exercises, the ASR module, the error detection module, and the whole system. For the final evaluation of the system, different groups of students of DL2 will use the system and fill in a questionnaire with which we can measure the students satisfaction in working with the system. Teachers of DL2 will then assess all sets of system prompts, student responses and system feedback for the quality of the feedback on the level of pronunciation, morphology and syntax.