%0 Journal Article
%T Voiced/unvoiced Decision Based on Recurrence Quantification Analysis<br>基于定量递归分析的清浊音判决
%A Yan Run-qiang
%A Zhu Yi-sheng
%A <br>闫润强
%A 朱贻盛
%J 电子与信息学报
%D 2007
%I 
%X Voiced/unvoiced decision is an important component in speech signal processing. In this paper, different topological structures in Recurrence Plots (RPs) are described for the different physical models of speech production. By statistically analyzing the determinism and the normalized maximal length of diagonal structures acquired from Recurrence Quantification Analysis (RQA), a flexible and efficient decision framework is proposed. Comparing with some traditional methods, the proposed algorithm has lower wrong decision rate. The method provides a new way for feature extraction and speech recognition.
%K Voiced/unvoiced decision
%K Speech dynamics
%K Recurrence plot
%K Recurrence quantification analysis
%K Feature extraction<br>清浊音判决
%K 语音动力学
%K 递归图
%K 定量递归分析
%K 特征提取
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=EFC0377B03BD8D0EF4BBB548AC5F739A&aid=26F10A3DEED7B269&yid=A732AF04DDA03BB3&vid=771469D9D58C34FF&iid=DF92D298D3FF1E6E&sid=10AEA069F4433410&eid=0CCE46DAE11318DE&journal_id=1009-5896&journal_name=电子与信息学报&referenced_num=0&reference_num=11