蚁群算法在语音识别中的应用研究  

Study on the Application of the Ant Colony Algorithm in Speech Recognition

作　　者：黄涛[1] 肖宜[1] 

机构地区：[1]武汉理工大学信息工程学院,湖北武汉430070

出　　处：《武汉理工大学学报（信息与管理工程版）》2007年第12期92-95,共4页Journal of Wuhan University of Technology：Information & Management Engineering

基　　金：武汉市重点科技攻关资助项目(20033001005-5-3)

摘　　要：提出了一种新的基于蚁群算法的语音识别中的动态时间规划方法——蚁群动态时间规划算法,并详细介绍了其基本原理、信息素更新规则,给出了系统流程图。经过理论分析与实验测试,证明了蚁群算法在这个系统中比传统的DTW算法更能提高识别率且更有效率。A new dynamic time programming algorithm in speech recognition based on the ant colony algorithm - - ant colony of dynamic time programming algorithm was proposed. The basic principles, pheromone refreshment rules were introduced in detail. The system flowchart was also presented. By theoretical analysis and experimental testing it proves that the ant colony algorithm used in this system can raise the recognition rate and is more efficient than traditional DTW algorithm.

关 键 词：蚁群算法 语音识别 识别率 

分 类 号：TN912.34[电子电信—通信与信息系统]