Full metadata record
DC FieldValueLanguage
dc.contributor.author盧維藩en_US
dc.contributor.authorLU, WEI-FANen_US
dc.contributor.author魏哲和en_US
dc.contributor.author陳信宏en_US
dc.contributor.authorWEI, ZHE-HEen_US
dc.contributor.authorCHEN, XIN-HONGen_US
dc.date.accessioned2014-12-12T02:03:09Z-
dc.date.available2014-12-12T02:03:09Z-
dc.date.issued1984en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#NT732436013en_US
dc.identifier.urihttp://hdl.handle.net/11536/52111-
dc.description.abstract本文提出一國語單字語音分段法:運用語音中的四種特徵(feature)--通過零點 率(zwro crossing rate),能量的對數值(log energy),將一國語單音字分割成 ”無聲音””前母音”,”中後母音”及”鼻音”等四段。 本文劑提出一應用分段法之特定語者國語單字辨認系統。此系統依據分段結果,對預 存之辨認字模(pattern)作先行之分類,以減少須分辨之字數,再應用分段之時軸 線性對應(segment linear timre warping )以決定字模之相似程度。以十個中文 數字(零一九)作測試,對四位發音者,本系統可得平均95%之正確辨認率。zh_TW
dc.language.isozh_TWen_US
dc.subject對數值zh_TW
dc.subject極點頻率zh_TW
dc.subject特徵zh_TW
dc.subject通過零點率zh_TW
dc.subject等化殘餘能量zh_TW
dc.subject字模zh_TW
dc.subject分段時軸線性對應zh_TW
dc.subjectLOG-ENERGYen_US
dc.subjectPOLE-FREQUCNCEen_US
dc.subjectFEATUREen_US
dc.subjectZERO-CROSSING-RATEen_US
dc.subjectNORMALIZED-RESIDUAL-ENERGYen_US
dc.subjectPATTERNen_US
dc.subjectSLTWen_US
dc.title應用分段法與時軸線性對應之國語單字辨認zh_TW
dc.typeThesisen_US
dc.contributor.department電信工程研究所zh_TW
Appears in Collections:Thesis