A preliminary study on ASR-based detection of Chinese mispronunciation by Japanese learners

Detecting mispronunciations produced by non-native speakers and providing detailed instructive feedbacks are desired in computer assisted pronunciation training system (CAPT), as it is helpful to L2 learners to improve their pronunciation more effectively. In this paper, we present our preliminary study on detecting phonetic segmental mispronunciations on account of the erroneous articulation tendencies, including the place of articulation and the manner of articulation. Through modeling and detecting these error patterns, feedbacks based on articulation-placement and articulation-manner could be given. Moreover, Japanese learners of Chinese are focused on in this study. The experimental results show that the approach can detect the mostly representative pronunciation errors moderately well, achieving a false rejection rate of 8.0% and a false acceptance rate 32.6%. The diagnostic accuracy is 86.0%.