한국인 영어학습자 발화의 자동음성인식을 위한 영어 음성사전 구성
Implementation of a non-native pronunciation dictionary for automatic recognition of utterances by Korean learners of English
1
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Abstract
Implementation of a non-native pronunciation dictionary for automatic recognition of utterances by Korean learners of English Jang, Tae-Yeoub This paper introduces a way of enhancing automatic speech recognition systems in processing non-native speakers' utterances. The key procedure is to design and provide an English pronunciation dictionary which includes frequent error pronunciations by Korean learners as if they were regular pronunciation variations. First, knowledge-based rules are collected to generate as many non-native variants as possible. Then the relative frequency of each variant is measured to select more frequent error-variants while discarding rare ones. In automatic recognition experiments with this dictionary, it is found that the word recognition performance increases considerably for Korean learners' incorrect pronunciation. Although utterances by Korean learners of English are the main target data of the current study, the proposed method is expected to be further available in other language environments.
참고문헌 (18)
- "음향 분석과 영어 발음교육" (2002), 한국문화사
- "한국인의 영어 음성 코퍼스 설계 및 구축", 46, pp.160~173 (2003)
- "한국어 영어학습자의 영어음성 데이터베이스 구축에 관한 연구", 35, pp.293~310 (2005)
- "영어음운론의 이해" (2005), 한국문화사
- "Speech recognition methods for non-native pronunciation variations^Giorgio Micca", pp.14~22 (1998), Strik etal
- "Proceedings of the IEEE 61", pp.268~278 (1973)
- "Generating non-native pronunciation variants for lexicon adaptation", 42(1), pp.109~123 (2004)
- "An HMM-based probabilistic lexicon", pp.57~62 (1998), Strik
- "An interactive English pronunciation dictionary for Korean learners", pp.1677~1680 (2004), Jeju, Korea
- "Generation and selection of English pronunciation variations using knowledge-based rules and speech recognition techniques", 12(2), pp.362~675 (2006), The Phonology-Morphology Circle of Korea
- "Modelling pronunciation variation for Cantonese speech recognition" (2002), Estes Park, Colorado
- "A data-driven method for modeling pronunciation variation", 40, pp.517~534 (2003)
- "Detecting and correcting poor pronunciations for multiword units", pp.85~90 (1998)
- "Modeling pronunciation variation for automatic speech recognition" (1998), Rolduc, The Nethelands. European Speech Communication Association, University of Nijemegen
- "Lexicon adaptation for LVCSR: speaker idiosyncracies, non-native speakers, and pronunciation choice" (2002)
- "Pronunciation modeling for ASR-knowledge-based and data-derived methods", 17(1), pp.69~85 (2003)
- "On the importance of exception and cross-word rules for the data-driven creation of Lexica for ASR", pp.589~593 (2000)
- "HTK Book" (1996)