计算机工程与应用Issue(15)：137-143,7.DOI:10.3778/j.issn.1002-8331.1703-0337
基于回溯搜索优化的卷积混合语音盲分离
Speech convolutive blind separation algorithm based on backtracking search optimization
摘要
Abstract
Aiming to overcome the limitation of initial separation matrix selection in Independent Vector Analysis(IVA), a convolutive blind speech separation algorithm based on backtracking search optimization is proposed. The sum of complex kurtosis of separated signals in each frequency point from IVA is used as the objective function. The Backtracking Search Optimization Algorithm(BSA)is used to adjust the initial separation matrix for better separation. In the separation process, complex Givens rotation transformation is used to transform separation matrix to rotation angle for reducing the coding dimension of BSA and the difficulty of optimization decreases. The blind speech separation experiments for convolutive mixture signals indicate that the proposed algorithm performs excellent separation results and the separation property is better than the basic IVA algorithm.关键词
语音盲分离/回溯搜索优化算法/卷积混合/独立矢量分析/Givens旋转变换Key words
speech blind separation/backtracking search optimization algorithm/convolutive mixture/independent vec-tor analysis/Givens rotation transformation分类
信息技术与安全科学引用本文复制引用
陈雷,韩大伟,郭艳菊,李媛媛,贾志成..基于回溯搜索优化的卷积混合语音盲分离[J].计算机工程与应用,2017,(15):137-143,7.基金项目
国家自然科学基金(No.61401307) （No.61401307）
中国博士后科学基金(No.2014M561184) （No.2014M561184）
天津市应用基础与前沿技术研究计划(No.15JCYBJC17100) （No.15JCYBJC17100）
天津市科技特派员项目(No.16JCTPJC48400). （No.16JCTPJC48400）
