Research of speech recognition based on Auto-Correlated Corner approach

摘要：

Based on Auto-Correlated Corner algorithm, we proposed a new method for pretreatment of speech signal in speech recognition system. The algorithm deleted semblable frames of speech signals which got after LPCC algorithm and MEL cepstrum transformation., and then solved characteristic redundancy efficiently. At last, we used speech recognition system based on spots-covering neural network to prove validity of Auto-Correlated Corner algorithm.

关键词： speech recognition MEL cepstrum transformation neural network Auto-Correlated Corner algorithm

作者: Fei lu Wenxiu He Chunyan xu

作者单位: Institute of Intelligent Information System, Information College, Zhejiang University of Technology, Hangzhou 310032, China

会议类型: 国际会议

会议名称: 2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)

会议地点: 广西桂林

会议语种:英文

页码: 3203-3206

在线出版日期: 2009-06-17（万方平台首次上网日期，不代表论文的发表时间）