Journal of South China University of Technology(Natural Science Edition) ›› 2012, Vol. 40 ›› Issue (3): 106-111.

• Electronics, Communication & Automation Technology • Previous Articles     Next Articles

Speaker Recognition Algorithm for Abnormal Speech Based on Abnormal Feature Weighting

He Jun  Li Yan-xiong  He Qian-hua  Li Wei   

  1. School of Electronic and Information Engineering,South China University of Technology,Guangzhou 510640,Guangdong,China
  • Received:2011-08-14 Revised:2011-10-11 Online:2012-03-25 Published:2012-02-01
  • Contact: 李艳雄(1980-) ，男，博士，讲师，主要从事信号处理及模式识别研究． E-mail: eeyxli@scut.edu.cn E-mail:hejun_723@126.com
  • About author:何俊(1978-) ，男，博士生，主要从事语音信号处理研究．
  • Supported by:

    国家自然科学基金资助项目( 60972132， 61101160) ; 广东省自然科学基金团队项目( 9351064101000003) ; 广东省自然科学基金博士科研启动项目( 10451064101004651) ; 华南理工大学中央高校基本科研业务费专项资金资助项目( 2011ZM0029)

PDF

1131

Abstract:

As the commonly-used weighting algorithm is inefficient in tracking the abnormal feature of abnormal speech,a speaker recognition algorithm for abnormal speech is proposed based on the abnormal feature weighting. In this algorithm,first,a feature template of normal speech is established by computing the probability distribution of MFCC features of each order in a large number of normal speech samples. Then,the K-L distance and the Euclidean distance are used to measure the differences between a given test speech and the normal speech templates and to further determine the K-L and the Euclidean weighting factors. Finally,the two weighting factors are used to weight the MFCC features of the test speech,and the weighted MFCC features are input in the Gaussian mixture model for the speaker recognition with abnormal speech. Experimental results show that the global recognition rates of the speaker recognition algorithms based on the K-L weighting and the Euclidean weighting are respectively 46.61% and 42.25%,while those of the algorithms with and without the weighting of speaker recognition contribution of each order feature are respectively only 39.68% and 36.36%.

Key words: abnormal speech, speaker recognition, abnormal feature weighting, K-L distance, weighting factor