Discriminative approaches for speech recognition based on continuous density HMM연속 밀도 HMM에 근거한 음성 인식에서의 분별적인 접근 방법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 348
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorUn, Chong-Kwan-
dc.contributor.advisor은종관-
dc.contributor.authorChung, Yong-Joo-
dc.contributor.author정용주-
dc.date.accessioned2011-12-14-
dc.date.available2011-12-14-
dc.date.issued1995-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=101743&flag=dissertation-
dc.identifier.urihttp://hdl.handle.net/10203/36300-
dc.description학위논문(박사) - 한국과학기술원 : 전기및전자공학과, 1995.8, [ vi, 131 p. ]-
dc.description.abstractHidden Markov Model (HMM) has become increasingly popular for speech recognition. Although it is true that HMM is good at modeling the stationary and sequential characteristics of speech signal, it has some drawbacks. One of the most frequently criticized aspects of HMM is its weak discrimination ability between competing classes. In this dissertation work, we present various methods to improve discrimination based on continuous density HMM. To evaluate the performance of the proposed methods, we use two sets of speech materials. One is speech for speaker-independent continuous speech recognition and the other is that for speaker-independent isolated word recognition. First, a discriminative modeling algorithm based on continuous density HMM has been studied. The proposed algorithm assigns different numbers of mixtures to each state of HMM by considering the acoustical variabilities. The variabilities are measured by the change of the entropy information when the number of mixtures is increased. In determining the number of mixtures, a competitive method which takes into account the information of different classes is employed. To obtain a more reliable segmentation information, the use of a training algorithm alternating the increment of the number of mixtures and the segmental k-means training is proposed. The proposed algorithm reduces the error rate considerably compared with a conventional HMM with a fixed number of mixtures in all states. Second, a new approach of using multilayer perceptrons (MLPs) in combination with HMMs is proposed. The MLP outputs are used as the state-dependent weightings of HMM likelihoods. MLP is trained for phoneme classification using the segmentation information which is obtained from the Viterbi alignment of HMM. Two independent MLPs for different parameter sets are trained with inputs of multiple context frames. The phoneme classification rate is considerably enhanced when their outputs are multiplied together. And, a relatio...eng
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectHMM-
dc.subjectSpeech Recognition-
dc.subjectDiscriminative Approach-
dc.subject분별적 방법-
dc.subjectHMM-
dc.subject음성인식-
dc.titleDiscriminative approaches for speech recognition based on continuous density HMM-
dc.title.alternative연속 밀도 HMM에 근거한 음성 인식에서의 분별적인 접근 방법-
dc.typeThesis(Ph.D)-
dc.identifier.CNRN101743/325007-
dc.description.department한국과학기술원 : 전기및전자공학과, -
dc.identifier.uid000885449-
dc.contributor.localauthorUn, Chong-Kwan-
dc.contributor.localauthor은종관-
Appears in Collection
EE-Theses_Ph.D.(박사논문)
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