메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
저널정보
한국어학회 한국어학 한국어학 제17권
발행연도
2002.12
수록면
163 - 179 (17page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
This study aims to introduce a way of verifying Korean phonological and phonetic processes using Automatic Speech Recognition techniques. It attempts to tackle the problems of the traditional ways in which variability and optionality of various processes are not dealt with properly. There are a few separate stages First, an automatic phone recogniser is constructed. The Hidden Markov Model (HMM) statistical recognition technique is employed to construct a Korean phone recogniser. Second. a target process is selected for verification. In the current study, the well-known Korean lenis stop voicing rule was chosen, as the traditional phonological description of this rule has been found to be problematic. Then the relevant speech data tokens which contain the segments located in the environment of voicing rule application, are selected from a corpus. A relatively large amount of speech recognition corpus is used instead of highly controlled speech data artificially designed for a specific phonetic experiment. Consequently, automatic statistical analyses. rather than intuitive judgment, are also adopted and that performance deterioration caused by inevitable errors of the phone recogniser can be alleviated thanks to the statistical averaging effect. After the recogniser is run on the data tokens. the binary evaluation results (ie., whether the rule has applied or not) are collected and interpreted through statistical parameters. It is revealed that there are many cases of phonetic outputs realised without having been influenced by the rule even though they are subject to the rule application environments. This fact suggests that the Korean lenis stop voicing rule need to be reinvestigated and re-described. Though only one rule has been under consideration in this research, many other phonological rules and phonetic constraints can be verified in the same way. It is especially meaningful that the quantitative method of speech technology can be utilized in verifying linguistic or phonetic phenomena.

목차

등록된 정보가 없습니다.

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2016-701-002266438