计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (17): 148-150.

• 数据库、信号与信息处理 • 上一篇    下一篇

基于概率神经网络的汉语耳语音识别系统

荣 薇1,陶 智1,顾济华1,赵鹤鸣2   

  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:2007-12-07 修回日期:2008-04-14 出版日期:2008-06-11 发布日期:2008-06-11
  • 通讯作者: 荣 薇

Identification of Chinese whispered speech based on PNN

RONG Wei1,TAO Zhi1,GU Ji-hua1,ZHAO He-ming2   

  1. 1.School of Phys. Sci. and Tech.,Suzhou University,Suzhou,Jiangsu 215006,China
    2.Dept. of Electron,School of Information,Suzhou University,Suzhou,Jiangsu 215006,China
  • Received:2007-12-07 Revised:2008-04-14 Online:2008-06-11 Published:2008-06-11
  • Contact: RONG Wei

摘要: 以提高汉语耳语的识别率为目的,提出了基于概率神经网(PNN)的语音识别系统。实验结果说明该方法提高了系统的识别率,大大缩短了识别时间,提高了整个系统的实时性。在小字库内得出的识别率为94.7%。

Abstract: In order to improve the rate of identification of the whispered speech,this paper puts forward a speech recognition model based on Probabilistic Neural Network(PNN).The experimental results demonstrate that this methed can improve the performance of the whispered speaker recognition system.A recognition rate of 94.7% is obtained when a small Chinese isolated word database is tested.