The Improvement of HMM Algorithm using wavelet de-noising in speech recognition

摘要：

Based on primary HMM algorithm, this paper discusses an improving algorithm of HMM and uses wavelet algorithm to reduce signal noise and then signal reconstruction. The improved algorithm uses MATLAB to carry out simulation test. Through setting appropriate wavelet soft threshold value, the test result shows that the improved algorithm will improve obviously speech recognition efficiency compared with primary HMM algorithm.

关键词： HMM Wavelet Speech recognition

作者: ZHOU Dexiang WANG Xianrong

作者单位: College of Information Science and TechnologyHenan University of Technology Zhengzhou, China College of Information Science and Technology Henan University of Technology Zhengzhou, China

会议类型: 国际会议

会议名称: 2010 3rd International Conference on Advanced Computer Theory and Engineering(2010年第三届先进计算机理论与工程国际会议 ICACTE 2010)

会议地点: 成都

会议语种:英文

页码: 1-4

在线出版日期: 2010-08-20（万方平台首次上网日期，不代表论文的发表时间）