RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기
    KCI등재

    코퍼스 기반 음성합성기를 위한 합성단위 경계 스펙트럼 평탄화 알고리즘 = A Spectral Smoothing Algorithm for Unit Concatenating Speech Synthesis

    한글로보기

    https://www.riss.kr/link?id=A100900667

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
    • 오류접수

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    Speech unit concatenation with a large database is presently the most popular method for speech synthesis. In this approach, the mismatches at the unit boundaries are unavoidable and become one of the reasons for quality degradation. This paper proposes an algorithm to reduce undesired discontinuities between the subsequent units. Optimal matching points are calculated in two steps. Firstly, the fullback-Leibler distance measurement is utilized for the spectral matching, then the unit sliding and the overlap windowing are used for the waveform matching. The proposed algorithm is implemented for the corpus-based unit concatenating Korean text-to-speech system that has an automatically labeled database. Experimental results show that our algorithm is fairly better than the raw concatenation or the overlap smoothing method.
    번역하기

    Speech unit concatenation with a large database is presently the most popular method for speech synthesis. In this approach, the mismatches at the unit boundaries are unavoidable and become one of the reasons for quality degradation. This paper propos...

    Speech unit concatenation with a large database is presently the most popular method for speech synthesis. In this approach, the mismatches at the unit boundaries are unavoidable and become one of the reasons for quality degradation. This paper proposes an algorithm to reduce undesired discontinuities between the subsequent units. Optimal matching points are calculated in two steps. Firstly, the fullback-Leibler distance measurement is utilized for the spectral matching, then the unit sliding and the overlap windowing are used for the waveform matching. The proposed algorithm is implemented for the corpus-based unit concatenating Korean text-to-speech system that has an automatically labeled database. Experimental results show that our algorithm is fairly better than the raw concatenation or the overlap smoothing method.

    더보기

    참고문헌 (Reference)

    1 "Unit selection in a concatenative speech synthesis system using a large speech database" 959-962, 1996

    2 "Synthesis of unseen context and spectral and pitch contour smoothing in concatenated text to speech synthesis" 469-472, 2002

    3 "Reducing audible spectral discontinuities" 39-51, 2001

    4 "Optimal coupling of diphones" Springer (chapter 23) : 293-304, 1997

    5 "On the reduction of concatenation artifacts in diphone synthesis" 1983-1986, 1998

    6 "High-quality prosodic modification of speech signals" 2446-2449, 1996

    7 "A comparison of spectral smoothing methods for segment concatenation based speech synthesis" Elsevier Science 36 : 343-374, 2002

    1 "Unit selection in a concatenative speech synthesis system using a large speech database" 959-962, 1996

    2 "Synthesis of unseen context and spectral and pitch contour smoothing in concatenated text to speech synthesis" 469-472, 2002

    3 "Reducing audible spectral discontinuities" 39-51, 2001

    4 "Optimal coupling of diphones" Springer (chapter 23) : 293-304, 1997

    5 "On the reduction of concatenation artifacts in diphone synthesis" 1983-1986, 1998

    6 "High-quality prosodic modification of speech signals" 2446-2449, 1996

    7 "A comparison of spectral smoothing methods for segment concatenation based speech synthesis" Elsevier Science 36 : 343-374, 2002

    더보기

    동일학술지(권/호) 다른 논문

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    인용정보 인용지수 설명보기

    학술지 이력

    학술지 이력
    연월일 이력구분 이력상세 등재구분
    2009-01-01 등재 학술지 폐간(기타)
    2007-01-24 학술지명변경 한글명 : 말소리</br>외국어명 : MALSORI KCI등재
    2006-01-01 등재 등재학술지 선정(등재후보2차) KCI등재
    2005-10-10 학술지명변경 한글명 : 말소리</br>외국어명 : MALSORI KCI등재후보
    2005-05-30 학술지명변경 한글명 : 말소리</br>외국어명 : MALSORI KCI등재후보
    2005-01-01 등재 등재후보 1차 PASS(등재후보1차) KCI등재후보
    2003-01-01 등재 등재후보학술지 선정(신규평가) KCI등재후보
    더보기

    이 자료와 함께 이용한 RISS 자료

    나만을 위한 추천자료

    해외이동버튼