计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (19): 30-31.

• 学术探讨 • 上一篇    下一篇

基于听觉感知和概率神经网络的语音识别模型

张晓俊1,陶 智1,顾济华1,赵鹤鸣2,施晓敏1   

  1. 1.苏州大学 物理科学与技术学院,江苏 苏州 215006
    2.苏州大学 电子信息学院,江苏 苏州 215006
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-07-01 发布日期:2007-07-01
  • 通讯作者: 张晓俊

Speech recognition model based on auditory perception and Probabilistic Neural Network

ZHANG Xiao-jun1,TAO Zhi1,GU Ji-hua1,ZHAO He-ming2,SHI Xiao-min1   

  1. 1.Department of Physics,School of Science,Suzhou University,Suzhou,Jiangsu 215006,China
    2.Department of Electron,School of Information,Suzhou University,Suzhou,Jiangsu 215006,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-07-01 Published:2007-07-01
  • Contact: ZHANG Xiao-jun

摘要: 提出了一种基于Bark子波变换和概率神经网络(PNN)的语音识别模型。利用符合人耳听觉特性的Bark滤波器组进行信号重构并提取语音特征,然后利用训练好的概率神经网络进行识别。通过训练大量语音样本来构成语音识别库,并建立综合识别系统。实验结果表明该方法与传统的LPCC/DTW和MFCC/DWT方法相比,识别率分别提高了14.9%和10.1%,达到了96.9%的识别率。

Abstract: The paper proposes a speech recognition model based on Bark Wavelet Transform and Probabilistic Neural Network(PNN).According to the group of filters which is similar to human auditory system,reconstruct the signal to abstract speech features then do the recognition work by trained PNN.By training a large number of speech samples,speech identification database is constructed,and the integrated recognition system is then built.The experiment results show that comparing with traditional ways of LPCC/DTW and MFCC/DTW,this method can increase the recognition rate by 14.9% and 10.1%,and it can attain recognition rate of 96.9%.