HMM-based note onset detection of natural humming for query by humming systems자연스러운 흥얼 거림 거색 시스템을 위한 은닉 마르코프 모델 기반의 음의 시작 위치 추출

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 616
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorYoo, Chang-Dong-
dc.contributor.advisor유창동-
dc.contributor.authorKim, Jae-Wook-
dc.contributor.author김재욱-
dc.date.accessioned2011-12-14T01:35:46Z-
dc.date.available2011-12-14T01:35:46Z-
dc.date.issued2010-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=419867&flag=dissertation-
dc.identifier.urihttp://hdl.handle.net/10203/36654-
dc.description학위논문(석사) - 한국과학기술원 : 전기 및 전자공학과, 2010.2, [ vii, 37 p. ]-
dc.description.abstractIn this paper, a Hidden Markov Model (HMM)-based note onset detector for Query by humming (QBH) systems is proposed. Until now, most QBH systems have restricted the user to sing each note using predefined humming syllables instead of humming in a natural fashion. This restriction is applied to induce hard onsets which allows for more accurate onset detection at the cost of unnatural interaction. The considered note onset detector allows users to either sing using predefined humming syllables or hum using gliding nasal sounds. We defined three HMMs for our dictionary using log voicing degree and pitch variance as features: the silence model, the hard note model and the soft note model. The HMM-based onset detector decodes the input signal providing note onset information used for humming transcription. Experimental results show that the proposed algorithm outperforms conventional algorithms.eng
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectSoft Onsets-
dc.subjectNote Onset Detection-
dc.subjectNatural Humming-
dc.subjectQuery by Humming-
dc.subjectHMM-
dc.subject은닉 마르코프 모델-
dc.subject연음-
dc.subject음조 위치 추출-
dc.subject자연 허밍-
dc.subject허밍 검색-
dc.titleHMM-based note onset detection of natural humming for query by humming systems-
dc.title.alternative자연스러운 흥얼 거림 거색 시스템을 위한 은닉 마르코프 모델 기반의 음의 시작 위치 추출-
dc.typeThesis(Master)-
dc.identifier.CNRN419867/325007 -
dc.description.department한국과학기술원 : 전기 및 전자공학과, -
dc.identifier.uid020074132-
dc.contributor.localauthorYoo, Chang-Dong-
dc.contributor.localauthor유창동-
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0