정제 알고리즘을 이용한 한국인 화자의 영어 발화 자동 진단 시스템
Automatic Pronunciation Diagnosis System of Korean Students’ English Using Purification Algorithm
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
We propose an automatic pronunciation diagnosis system to evaluate the pronunciation of a foreign language without the uttered text. We recorded English utterances spoken by native and Korean speakers, and utterances spoken by Koreans are evaluated by native speakers based on three criteria: fluency, accuracy of phones and intonation. The system evaluates the utterances of test Korean speakers based on the differences of log-likelihood given two models: one is trained by English speech uttered by native speakers, and the other is trained by English speech uttered by Korean speakers. We also applied purification algorithm to increase class differentiability. The purification can detect and eliminate the non-speech frames such as short pauses, occlusive silences that do not help to discriminate between utterances. As the results, our proposed system has higher correlation with the human scores than the baseline system.
Abstract
We propose an automatic pronunciation diagnosis system to evaluate the pronunciation of a foreign language without the uttered text. We recorded English utterances spoken by native and Korean speakers, and utterances spoken by Koreans are evaluated by native speakers based on three criteria: fluency, accuracy of phones and intonation. The system evaluates the utterances of test Korean speakers based on the differences of log-likelihood given two models: one is trained by English speech uttered by native speakers, and the other is trained by English speech uttered by Korean speakers. We also applied purification algorithm to increase class differentiability. The purification can detect and eliminate the non-speech frames such as short pauses, occlusive silences that do not help to discriminate between utterances. As the results, our proposed system has higher correlation with the human scores than the baseline system.
참고문헌 (9)
- 김무중, "한국인을 위한 영어 발음 교정 시스템에 대한 성능 평가", 2003 대한음성학회 봄 학술대회, pp.71~74 (2003)
- 김효숙, "한국인을 위한 영어발음교정 시스템 'Dr. Speaking' 소개", 대한음성학회 창립 25주년 기념 학술대회, pp.47~50 (2002)
- 박전규, "발성 평가를 위한 영어 음성인식기의 개발", 2003 대한음성학회 가을 학술대회, pp.37~40 (2003)
- Anguera, X., "Purity algorithms for speaker diarization of meetings data", ICASSP, pp.1025~1028 (2006)
- Cucchiarini, C., "Different aspects of expert pronunciation quality ratings and their relation to scores produced by speech recognition algorithms", Speech Communication, 30(2), pp.109~119 (2000)
- Franco, H., "Automatic pronunciation scoring for language instruction", ICASSP, pp.1471~1474 (1997)
- Moustroufas, N., "Automatic pronunciation evaluation of foreign speakers using unknown text", Computer Speech & Language, 21(1), pp.219~230 (2007)
- Neumeyer, L., "Webgrader (tm): A multilingual pronunciation practice tool", Workshop on STiLL, pp.61~64 (1998)
- Neumeyer, L., "Automatic text-independent pronunciation scoring of foreign language student speech", ICSLP, pp.1457~1460 (1996)