Browse > Article
http://dx.doi.org/10.13064/KSSS.2015.7.3.139

Pronunciation Variation Patterns of Loanwords Produced by Korean and Grapheme-to-Phoneme Conversion Using Syllable-based Segmentation and Phonological Knowledge  

Ryu, Hyuksu (서울대학교)
Na, Minsu (서울대학교)
Chung, Minhwa (서울대학교)
Publication Information
Phonetics and Speech Sciences / v.7, no.3, 2015 , pp. 139-149 More about this Journal
Abstract
This paper aims to analyze pronunciation variations of loanwords produced by Korean and improve the performance of pronunciation modeling of loanwords in Korean by using syllable-based segmentation and phonological knowledge. The loanword text corpus used for our experiment consists of 14.5k words extracted from the frequently used words in set-top box, music, and point-of-interest (POI) domains. At first, pronunciations of loanwords in Korean are obtained by manual transcriptions, which are used as target pronunciations. The target pronunciations are compared with the standard pronunciation using confusion matrices for analysis of pronunciation variation patterns of loanwords. Based on the confusion matrices, three salient pronunciation variations of loanwords are identified such as tensification of fricative [s] and derounding of rounded vowel [ɥi] and [$w{\varepsilon}$]. In addition, a syllable-based segmentation method considering phonological knowledge is proposed for loanword pronunciation modeling. Performance of the baseline and the proposed method is measured using phone error rate (PER)/word error rate (WER) and F-score at various context spans. Experimental results show that the proposed method outperforms the baseline. We also observe that performance degrades when training and test sets come from different domains, which implies that loanword pronunciations are influenced by data domains. It is noteworthy that pronunciation modeling for loanwords is enhanced by reflecting phonological knowledge. The loanword pronunciation modeling in Korean proposed in this paper can be used for automatic speech recognition of application interface such as navigation systems and set-top boxes and for computer-assisted pronunciation training for Korean learners of English.
Keywords
loanwords; pronunciation variation; syllable-based; grapheme-to-phoneme; Korean;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Chung, K. (2003). Transcription of Loanwords and Pronunciation of Foreign Languages. Studies in foreign language education. No. 17, 185-214. (정국 (2003). 외래어 표기법과 외국어 발음. 외국어교육연구 17호, 185-214.)
2 Jouvet, D., Fohr, D. & Illina, I. (2012). Evaluating grapheme-to-phoneme converters in automatic speech recognition context. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4821-4824.
3 Kang, H. (1996). English loanword in Korean. Studies in Phonetics, Phonology, and Morphology. Vol. 2, 21-47.
4 Kim, B., Lee, G. G. & Lee, J-H. (2002). Morpheme-based grapheme to phoneme conversion using phonetic patterns and morphophonemic connectivity information, ACM Transactions on Asian Language Information Processing. Vol. 1, No. 1, 65-82.   DOI
5 Lee, E. K. (1998). Usage of Loanwords in Multimedia. Saegugeosaenghwal. Vol. 8, 41-59. (이은경 (1998). 방송 분야의 외래어 사용. 새국어생활 8권, 41-59.)
6 Lee, J. & Lee, G. G. (2009). A data-driven grapheme-to-phoneme conversion method using dynamic contextual converting rules for Korean TTS systems. Computer Speech and Language. Vol. 23, 423-434.   DOI
7 Lee, K-N. & Chung, M. (2007). Morpheme-based modeling of pronunciation variation for large vocabulary continuous speech recognition in Korean. Transactions on Information and Systems. Vol. E90-D, No. 7, 1063-1072.   DOI
8 Modipa, T. & Davel, M. H. (2010). Pronunciation modelling of foreign words for Sepedi ASR. Proceedings of 21st Annual Symposium of the Pattern Recognition Association of South Africa (PRASA). 185-89.
9 Ryu, H. & Chung, M. (2014). Pronunciation variations of loanwords produced by Korean speakers. Proceedings of Conference of Korean Society of Speech Sciences (KSSS). 173-174. (류혁수, 정민화. (2014). 한국인 화자의 외래어 발음 변이 양 상. 한국음성학회 가을 학술대회 발표논문집, 141-142.)
10 Bang, J., Lee, J., Lee, G. G., & Chung, M. (2014). Pronunciation variants prediction method to detect mispronunciations by Korean learners of English. ACM Transactions on Asian Language Information Processing (TALIP). Vol. 13, No. 4, 1-21.
11 Bisani, M. & Ney, H. (2008). Joint-sequence models for grapheme-to-phoneme conversion. Speech Communication. Vol. 50 No. 5, 434-451.   DOI
12 Cha, J. E. (2007). A study on the standard pronunciation of the words of foreign origin and related matters. Korean Linguistics. Vol. 35, 363-390. (차재은 (2007). 외래어 표준 발음 문제에 대한 고찰. 한국어학 35권, 363-390.)
13 Choi, H. (2001). A research on loanword pronunciations. Seoul: The National Institute of the Korean Language. (최혜원 (2001). 외래어 발음 실태 조사. 국립국어연구원.)
14 Wang, L. & Tong, R. (2014). Pronunciation modeling of foreign words for mandarin ASR by considering the effect of language transfer. Proceedings of INTERSPEECH 2014. 1443-1447.
15 Schlippe, T., Ochs, S. & Schultz, T. (2012). Grapheme-to-phoneme model generation for Indo-European languages. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 4801-4804.
16 Schlippe, T., Quaschningk, W. & Schultz, T. (2014). Combining grapheme-to-phoneme enhanced pronunciation generation in low-resource scenarios. Proceedings of 4th Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU '14). 139-145.
17 The National Institute of the Korean Language. (2015). The regulation concerning Hangeul transcription of loanwords. http://www.korean.go.kr/front/page/pageView.do?page_id=P000104&mn_id=97 (국립국어원. (2015). 외래어 표기법 규정. http://www.korean.go.kr/front/page/pageView.do?page_id=P000104&mn_id=97.)
18 Yoon, K. & Brew, C. (2006). A linguistically motivated approach to grapheme-to-phoneme conversion for Korean. Computer Speech and Language. Vol. 20, 357-381.   DOI
19 Yurn, G. D. (2006). In Justification of "Jjajangmyeon". Korean Linguistics. Vol. 30, 181-205. (연규동 (2006). "짜장면"을 위한 변명. 한국어학 30권, 181-205.)