한국인 영어 학습자의 발음 정확성 자동 측정 방법에 대한 연구

A Study on Automatic Measurement of Pronunciation Accuracy of English Speech Produced by Korean Learners of English

  The purpose of this research is to develop a device that can automatically measure pronunciation accuracy of English speech produced by Korean learners of English. Pronunciation accuracy will be measured mainly in two areas; suprasegmental and segmental areas. In suprasegmental area, intonation and word stress of Korean English learners will be traced and compared with those of native speakers by way of statistical methods using tilt parameters. Durations of phones are also examined to measure speakers" fluency of their pronunciations. In doing so, statistical duration modelling from a large speech database using CART will be used. For segmental measurement of pronunciation accuracy, acoustic probability of a phone, which is a byproduct of the forced alignment, will be a basis of scoring the accuracy. The final score will be a feedback to the learners to improve their pronunciation.