English and Japanese CALL Systems Developed at Kyoto University

This paper gives an overview of the English and Japanese CALL systems which have been developed at Kyoto University. Both systems incorporate automatic speech recognition (ASR) technologies to detect pronunciation errors. In order to cope with non-native speech, error prediction mechanisms are prepared based on linguistic knowledge and corpus-based decision tree learning. Several choices of acoustic modeling for non-native speech including erroneous pronunciations are also investigated. The English CALL system is designed for Japanese college students so that they can introduce Japanese cultures to foreign people, thus the acoustic model and error prediction are tuned to the specific native language (L1=Japanese). On the other hand, the Japanese CALL system is for foreign visitors of any L1, and focuses on basic-level sentence production and adopts GUI for easy practice.