文章摘要
杨庆涛,李昕,郑宇,张芸.实用语音识别的场景标记辅助系统[J].声学技术,2006,(5):478~481
实用语音识别的场景标记辅助系统
Multimedia scene labeling based on speech
投稿时间:2005-10-13  修订日期:2006-01-06
DOI:
中文关键词: 媒体资产管理  语音标引  EBF网络
英文关键词: media asset management  speech-based label  EBF neural network
基金项目:上海市教委青年基金(04AB72);上海市科委启明星计划资助(04QMX1441)
作者单位
杨庆涛 上海大学机电工程与自动化学院, 上海, 200072 
李昕 上海大学机电工程与自动化学院, 上海, 200072
南京大学电子科学与工程系, 南京, 210093 
郑宇 上海大学计算机学院, 上海, 200072 
张芸 上海大学机电工程与自动化学院, 上海, 200072 
摘要点击次数: 700
全文下载次数: 892
中文摘要:
      标引是通过给音频-视频数据加入标记,对其内容进行描述,以便于信息的检索和查询。语音标引在媒体资产管理中扮演了很重要的脚色。介绍了一种基于EBF网络的语音标引辅助系统,该系统可自动识别标引员所说的短语,辅助标引员在视频媒体上实现标引。系统从语句中将这些短语分割出来,并通过EBF神经网络进行建模。实验结果证明,该系统具有实用性,在媒体资产管理方面有良好的应用前景。
英文摘要:
      The main objective of the indexing process is to assign labels to the audio-visual data in order to describe its content.Audio indexing plays a key role in this process.In this paper,a speech-based manmachine labeling system for media asset management is presented.The system recognizes the phrases spoken by the human annotator automatically and assists him to mark up shots of subjects in a video sequence.The phrases are segmented from short sentences and modeled by the elliptical basis function(EBF) networks.Experimental results indicate that the speech-based labeling system is practical and has great promise for media asset management.
查看全文   查看/发表评论  下载PDF阅读器
关闭
function PdfOpen(url){ var win="toolbar=no,location=no,directories=no,status=yes,menubar=yes,scrollbars=yes,resizable=yes"; window.open(url,"",win); } function openWin(url,w,h){ var win="toolbar=no,location=no,directories=no,status=no,menubar=no,scrollbars=yes,resizable=no,width=" + w + ",height=" + h; controlWindow=window.open(url,"",win); } &et=AFD807188AF05852150FB80A770DD02ECD39053DFC88EB9D1233DC6C05479AE67782CBDA60396C3B9BA1958ABD577017&pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=84529CA2B2E519AC&jid=DDCFCD5ACE1B1E5A6D46213553C850CA&yid=37904DC365DD7266&aid=&vid=&iid=94C357A881DFC066&sid=A94616C4391AA5EF&eid=283B38DAD0D068F3&fileno=20060518&flag=1&is_more=0">