%0 Journal Article
%T Articulatory feature based on audio visual speech recognition model<br>基于发音特征的音/视频双流语音识别模型*
%A SONG Pei yan
%A JIANG Dong mei
%A WANG Feng na
%A <br>宋培岩
%A 蒋冬梅
%A 王风娜
%J 计算机应用研究
%D 2009
%I 
%X This paper presented an articulatory feature (AF)-based multi-stream dynamic Bayesian networks (DBN) model (AF_AV_DBN) for audio visual speech recognition. Defined conditional probability of each node and degree of asynchrony between AFs,and carried out speech recognition experiments on an audio visual connected digit database. Comparing results with the other two single stream DBN models (audio-only model and video-only model) show that AF_AV_DBN performs the best when the signal-noise ratio on the audio s...
%K dynamic Bayesian network(DBN)
%K articulatory feature
%K audio visual
%K speech recognition<br>动态贝叶斯网络
%K 发音特征
%K 音/视频
%K 语音识别
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=F1E8EA0F02FCC15C16A3C72239436080&yid=DE12191FBD62783C&vid=96C778EE049EE47D&iid=DF92D298D3FF1E6E&sid=C9E61AB37F867E3C&eid=2C1BC72871CFCFEC&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=8