计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (35): 129-131.DOI: 10.3778/j.issn.1002-8331.2009.35.039

• 数据库、信号与信息处理 • 上一篇    下一篇

基于差分特征和高斯混合模型的湖南方言识别

王岐学,钱盛友,赵新民   

  1. 湖南师范大学 物理与信息科学学院,长沙 410081
  • 收稿日期:2009-07-28 修回日期:2009-10-19 出版日期:2009-12-11 发布日期:2009-12-11
  • 通讯作者: 王岐学

Hunan dialects identification based on GMM and difference speech feature

WANG Qi-xue,QIAN Sheng-you,ZHAO Xin-min   

  1. College of Physics and Information Science,Hunan Normal University,Changsha 410081,China
  • Received:2009-07-28 Revised:2009-10-19 Online:2009-12-11 Published:2009-12-11
  • Contact: WANG Qi-xue

摘要: 语音的韵律是区分汉语方言的重要语音声学特征,而语音的差分特征是语音韵律的重要体现。采用差分特征ΔMFCC和ΔΔMFCC作为特征参数,用高斯混合模型(GMM)作为训练模型,通过计算测试样本的似然概率来识别方言的类型。用该方法对长沙方言、邵阳方言、衡阳方言和普通话进行了识别研究,并与采用MFCC作为特征参数的识别效果进行了比较。实验结果表明差分特征具有识别率高、抗噪声性能更好等优点。

Abstract: Rhythm of speech is an important acoustic distinction between different Chinese dialects,and the difference feature is an important reflection of rhythm.While difference features ΔMFCC & ΔΔMFCC are used as characteristic parameters and Gaussian Mixture Model(GMM) is used as a trained model,the dialect can be identified through calculating the likelihood probability of the test samples.Changsha dialect,Shaoyang dialect,Hengyang dialect and Mandarin have been investigated with this method,and its effect has been compared with the effect using MFFC as characteristic parameters.Experiment results show that a more high recognition rate and better anti-noise performance can be obtained by GMM trained with difference feature.

中图分类号: