Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (7): 123-125.

Previous Articles     Next Articles

study and recognition of pathological voice

CHEN Chengyi1, GAO Junfen2   

  1. 1.Liuzhou Railway Vocational Technical College, Liuzhou, Guangxi 545007, China
    2.Guangxi Normal University, Guilin, Guangxi 541004, China
  • Online:2013-04-01 Published:2013-04-15

病态嗓音的识别与研究

陈承义1,高俊芬2   

  1. 1.柳州铁道职业技术学院,广西 柳州 545007
    2.广西师范大学,广西 桂林 541004

Abstract: By analyzing the mechanism of pronunciation, normal and pathological voice of traditional acoustic parameters:fundamental frequency, formant, Mel Frequency Cepstrum Coefficient(MFCC), and non-linear feature parameters:box-counting dimension and intercept, are extracted as feature vectors of recognition of pathological voice. 156 normal voice samples and 146 pathological voice samples are recognized based on Gaussian Mixture Model(GMM). The results show that the nonlinear feature parameters of box-counting dimension and intercept can well distinguish between normal and pathological voice. The combination of box-counting dimension, intercept and the traditional acoustic parameters-fundamental frequency and formant can achieve a better recognition rate of 92.60%.

Key words: Gaussian Mixture Model(GMM), pathological voice, box-counting dimension, intercept

摘要: 通过分析嗓音的发音机理,提取正常与病态嗓音的传统声学参数:基频、共振峰、Mel倒谱系数(MFCC),以及非线性特征参数:计盒维数与截距,作为病态嗓音识别的特征矢量集。应用高斯混合模型(GMM)对156例正常嗓音与146例病态嗓音进行建模与识别。结果表明:非线性特征参数计盒维数与截距能很好地区分正常与病态嗓音,它们与传统声学参数基频和共振峰的组合,能够取得92.60%的识别率。

关键词: 高斯混合模型, 病态嗓音, 计盒维数, 截距