Browse > Article

Statistical Analysis of Korean Phonological Variations Using a Grapheme-to-phoneme System  

이경님 (서강대학교 컴퓨터학과 음성언어처리연구실)
정민화 (서강대학교 컴퓨터학과 음성언어처리연구실)
Abstract
We present a statistical analysis of Korean phonological variations using a Grapheme-to-Phoneme (GPT) system. The GTP system used for experiments generates pronunciation variants by applying rules modeling obligatory and optional phonemic changes and allophonic changes. These rules are derived form morphophonological analysis and government standard pronunciation rules. The GTP system is optimized for continuous speech recognition by generating phonetic transcriptions for training and constructing a pronunciation dictionary for recognition. In this paper, we describe Korean phonological variations by analyzing the statistics of phonemic change rule applications for the 60,000 sentences in the Samsung PBS Speech DB. Our results show that the most frequently happening obligatory phonemic variations are in the order of liaison, tensification, aspirationalization, and nasalization of obstruent, and that the most frequently happening optional phonemic variations are in the order of initial consonant h-deletion, insertion of final consonant with the same place of articulation as the next consonants, and deletion of final consonant with the same place of articulation as the next consonant's, These statistics can be used for improving the performance of speech recognition systems.
Keywords
Grapheme-to-phoneme system; Phonological variations; Pronunciation dictionary; Statistical analysis of Korean phonological rules;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Unlimited vocabulary grapheme-to-phoneme conversion for Korean TTS /
[ B.Kim;W.Lee;G.Lee;J.Lee ] / Proc. of ACL-COLING 98
2 /
[] / 표준어 규정, 문교부 고시
3 Letter-to-sound rules for automatic translation of english text to phonetics /
[ H.Elovitz;R.Johnson;A.Mchugh;J.Shore ] / IEEE Trans. Acoust. Speech, Signal Processing
4 /
[ 김흥규;강범모 ] / 한글 사용빈도의 분석
5 음소 문맥과 음운 변화 현상을 이용한 한국어 연속 음성 인식 /
[ 김한준 ] / 서강대학교 컴퓨터학과 석사학위 논문
6 Modeling pronunciation variation for ASR: Overview and comparison of methods /
[ H.Strik;C.Cucchiarini ] / Proc. of the ESCA workshop Modeling pronunciation variation for automatic speech recognition
7 한국어 연속음성 인식을 위한 발음열 자동 생성 /
[ 이경님;전재훈;정민화 ] / 한국음향학회지   과학기술학회마을
8 /
[ J.Clark;C.Yallop ] / An Introduction to Phonetics and Phonology
9 /
[ 한국방송공사 ] / 표준 한국어 발음 대사전
10 공동 이용을 위한 단어음성DB의 구축 및 PBS 설계에 관한 검토 /
[ 김봉완;김종진;김선태;김태환;김영일;이용주 ] / 제13회 음성통신 및 신호처리워크샵 논문집
11 /
[ 이기문;김진우;이상억 ] / 국어음운론