메뉴 건너뛰기
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)
고객센터 ENG
주제분류

피인용 0

검색

    초록·키워드

    In this paper, we present a new pitch determination method for speech analysis, namely modified EGG-based and modified LP Error-based algorithm with variable threshold. We will show that these algorithms provide robust pitch estimates on a period by period basis and reliable pitch detection in quasi-periodic as well as in aperiodic speech signals. To verify the performance of the proposed pitch detectors, a standard pitch determination, a SIFT[1] algorithm, is used to evaluate and compare the proposed algorithms for its capacity to detect and identify the patterns of aperiodic/quasi-periodic voice vibration in natural human speech.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-ECN-0101-2014-569-001015313