음성인식기를 이용한 한국인의 외국어 발화오류 자동 검출

Automatic Detection of Mispronunciation Using Phoneme Recognition For Foreign Language Instruction

An automatic pronunciation correction system provides learners with correction guidelines for each mispronunciation. In this paper we propose an HMM based speech recognizer which automatically classifies pronunciation errors when Korean speak Japanese. For this purpose we also develop phoneme recognizers for Korean and Japanese. Experimental results show that the machine scores of the proposed recognizer correlate with expert ratings well.