首页 | 本学科首页   官方微博 | 高级检索  
     

基于LM算法的神经网络语音识别
引用本文:葛玲,贾志成,夏克文,王霞.基于LM算法的神经网络语音识别[J].计算机工程与设计,2006,27(14):2534-2536,2539.
作者姓名:葛玲  贾志成  夏克文  王霞
作者单位:河北工业大学,信息工程学院,天津,300132
摘    要:由于语音识别中朵用标准BP算法存在的训练速度慢、容易陷入局部极小等问题,提出一种基于稳定、快速的Levenberg-Marquardt算法的神经网络语音识别方法,主要包括语音信号预处理、特征提取、网络结构优化设计、网络学习训练和语音识别等过程。其中网络隐含层节点数的选取采用黄金分割优选法。试验仿真表明,LM算法明显提高了网络训练速度,减少了训练时间,其效果优越于标准BP算法。

关 键 词:神经网络  语音识别  标准BP算法  Levenberg-Marquardt算法  黄金分割优选法
文章编号:1000-7024(2006)14-2534-03
收稿时间:2005-05-18
修稿时间:2005-05-18

Neural network speech recognition based on LM algorithm
GE Ling,JIA Zhi-cheng,XIA Ke-wen,WANG Xia.Neural network speech recognition based on LM algorithm[J].Computer Engineering and Design,2006,27(14):2534-2536,2539.
Authors:GE Ling  JIA Zhi-cheng  XIA Ke-wen  WANG Xia
Affiliation:School of Information Engineering, Hebei University of Technology, Tianjin 300132, China
Abstract:For the defects of standard BP algorithm used in speech recognition, such as very slow training speed, very easy to falling into local minimization, and so on, a new method of neural network speech recognition is presented based on a stable and fast Levenberg- Marquardt algorithm, which includes following processing steps, speech signal preproeessing, characteristic extracting, optimization design of network structure, network training and speech recognizing. Besides, an optimization algorithm based on the principle of golden section is adopted to design the number of hidden layer nodes in neural network. The simulation experiments shows that the Levenberg-Marquardt algorithm is superior to that of standard BP, which obviously quickens training speed and decreases training time, and the application effect is notable.
Keywords:neural network  speech recognition  standard BP algorithm  levenberg-marquardt algorithm  golden section optimization algorithm
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号