화자종속모델을 사용한 HSMM 기반의 한국어 음색변환 HSMM-based Korean Voice Conversion Using Speaker Dependent Model

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 590
  • Download : 21
DC FieldValueLanguage
dc.contributor.author최, 지성-
dc.contributor.author한, 승호-
dc.contributor.author정, 상배-
dc.contributor.author김, 종진-
dc.contributor.author한, 민수-
dc.contributor.authorChoi, Jisung-
dc.contributor.authorHan, Seungho-
dc.contributor.authorJeong, Sangbae-
dc.contributor.authorKim, Jong-Jin-
dc.contributor.authorHahn, Minsoo-
dc.date.accessioned2011-11-08T04:23:44Z-
dc.date.available2011-11-08T04:23:44Z-
dc.date.issued2008-11-
dc.identifier.citation대한음성학회 학술대회논문집en
dc.identifier.urihttp://hdl.handle.net/10203/25521-
dc.description.abstractThis paper describes a voice conversion method for an HSMM(Hidden Semi-Markov model)―based speech synthesis system. Our HSMM system adopt a speaker dependent model which can be converted into a target speaker model through the adaptation process. The main purpose of this paper is to investigate the possibility that speaker adaptation method can be successfully applied even on the SD model instead of average voice model. By utilizing the SD model based HSMM system combined with MLLR(Maximum Likelihood Linear Regression) as an adaptation process, it will be shown that conversion both of spectral and prosody information such as F0 and phone duration are sincerely reflected on the synthesized speech.en
dc.language.isokoen
dc.publisher대한음성학회en
dc.title화자종속모델을 사용한 HSMM 기반의 한국어 음색변환en
dc.title.alternativeHSMM-based Korean Voice Conversion Using Speaker Dependent Modelen
dc.typeBooken

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0