Full metadata record
DC FieldValueLanguage
dc.contributor.author蔡富評en_US
dc.contributor.authorFu-Ping Tsaien_US
dc.contributor.author傅心家en_US
dc.contributor.authorHsin-Chia Fuen_US
dc.date.accessioned2014-12-12T02:55:15Z-
dc.date.available2014-12-12T02:55:15Z-
dc.date.issued2005en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#GT009317577en_US
dc.identifier.urihttp://hdl.handle.net/11536/78786-
dc.description.abstract語音資訊檢索主要是研究如何對大量的多媒體資訊(如廣播新聞),利用語音辨識技術,以自動的方式對於其內含的語音資訊建立起全文索引與檢索的機制。本篇論文主旨在針對台灣廣播新聞,在建立語音檢索的機制之前,需要針對電視新聞節目建立起自動新聞分析的系統,以偵測出新聞節目中主播的位置並切割新聞故事的問題作探討研究。近來許多新聞節目中主播音段常有明顯的背景音樂,為了正確的偵測出沒有背景音樂的主播音段,論文中提出結合BIC語者分段與分群以及語者識別的技術來偵測新聞中沒有背景音樂的主播音段。我們以台灣有線東森新聞台的新聞節目進行主播偵測的實驗,驗證所提的方法能正確偵測出沒有背景音樂的主播音段,論文最後更進一歩實作語音音節辨識並且成功建立起以音節為索引特徵之電視新聞語音檢索系統。zh_TW
dc.description.abstractThis thesis mainly describes broadcast news retrieval system for Mandarin Chinese. First, we need to construct automatically news analysis system to detect anchor segments in news program. Recently, we observed some anchor segments that have background music in many news programs. In order to correctly detect anchor segments without background music, we propose a method based on technologies such as BIC-Segmentation, BIC-Clustering and GMM-based speaker identification for TV news anchor detection. The experiment corpus is collected from daily news on ETT news program and the experiment result is good. Moreover, we integrate the proposed method and implement syllable-level indexing feature news spoken document retrieval system on TV news successfully.en_US
dc.language.isozh_TWen_US
dc.subject語音資訊檢索zh_TW
dc.subject語者分段zh_TW
dc.subject語者分群zh_TW
dc.subject語者識別zh_TW
dc.subjectSpeech Information Retrievalen_US
dc.subjectBIC Segmentationen_US
dc.subjectBIC Clusteringen_US
dc.subjectSpeaker Identificationen_US
dc.title電視新聞語音檢索之研究zh_TW
dc.titleThe Study of Spoken Document Retrieval on TV newsen_US
dc.typeThesisen_US
dc.contributor.department資訊科學與工程研究所zh_TW
Appears in Collections:Thesis


Files in This Item:

  1. 757701.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.