计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (30): 213-216.

• 工程与应用 • 上一篇    下一篇

基于改进LPCC和MFCC的汉语耳语音识别

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:1900-01-01 修回日期:1900-01-01 出版日期:2007-10-21 发布日期:2007-10-21
  • 通讯作者: 荣 薇

Identification of Chinese whispered speech based on modified LPCC and MFCC

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

  1. 1.School of Physical Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China
    2.School of Electronics and Information,Soochow University,Suzhou,Jiangsu 215006,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-21 Published:2007-10-21
  • Contact: RONG Wei

摘要: 以提高汉语耳语的识别率为目的,提出了将MFCC、LPCC及它们各自的动态参数等多种特征有效结合进行耳语识别的方法。实验结果说明了LPCC、MFCC结合动态参数可作为汉语耳语音识别的特征参数,且它们的结合提高了系统的识别率,在小字库内得出的识别率为94.5%。

Abstract: In order to improve the rate of identification of the whispered speech,this paper puts forward a method that combining efficiently more features such as MFCC and LPCC and their dynamic parameters and so on to acquire better recognition performance.The experimental results demonstrate that the LPCC and MFCC combine with the dynamic parameters features can be used as efficient parameters for the Chinese whispered speech recognition,and their combination improve the performance of the whispered speaker recognition system.A recognition rate of 94.5% is obtained when a small Chinese isolated word database is tested.