EI / SCOPUS / CSCD 收录

中文核心期刊

嗓音多频带非线性分析的声带病变识别

周强, 张晓俊, 顾济华, 赵鹤鸣, 朱俊杰, 陶智

周强, 张晓俊, 顾济华, 赵鹤鸣, 朱俊杰, 陶智. 嗓音多频带非线性分析的声带病变识别[J]. 声学学报, 2014, 39(1): 111-118. DOI: 10.15949/j.cnki.0371-0025.2014.01.013
引用本文: 周强, 张晓俊, 顾济华, 赵鹤鸣, 朱俊杰, 陶智. 嗓音多频带非线性分析的声带病变识别[J]. 声学学报, 2014, 39(1): 111-118. DOI: 10.15949/j.cnki.0371-0025.2014.01.013
ZHOU Qiang, ZHANG Xiaojun, GU Jihua, ZHAO Heming, ZHU Junjie, TAO Zhi. Vocal cords diseases detection by multi-band nonlinear analysis of voice[J]. ACTA ACUSTICA, 2014, 39(1): 111-118. DOI: 10.15949/j.cnki.0371-0025.2014.01.013
Citation: ZHOU Qiang, ZHANG Xiaojun, GU Jihua, ZHAO Heming, ZHU Junjie, TAO Zhi. Vocal cords diseases detection by multi-band nonlinear analysis of voice[J]. ACTA ACUSTICA, 2014, 39(1): 111-118. DOI: 10.15949/j.cnki.0371-0025.2014.01.013
周强, 张晓俊, 顾济华, 赵鹤鸣, 朱俊杰, 陶智. 嗓音多频带非线性分析的声带病变识别[J]. 声学学报, 2014, 39(1): 111-118. CSTR: 32049.14.11-2065.2014.01.013
引用本文: 周强, 张晓俊, 顾济华, 赵鹤鸣, 朱俊杰, 陶智. 嗓音多频带非线性分析的声带病变识别[J]. 声学学报, 2014, 39(1): 111-118. CSTR: 32049.14.11-2065.2014.01.013
ZHOU Qiang, ZHANG Xiaojun, GU Jihua, ZHAO Heming, ZHU Junjie, TAO Zhi. Vocal cords diseases detection by multi-band nonlinear analysis of voice[J]. ACTA ACUSTICA, 2014, 39(1): 111-118. CSTR: 32049.14.11-2065.2014.01.013
Citation: ZHOU Qiang, ZHANG Xiaojun, GU Jihua, ZHAO Heming, ZHU Junjie, TAO Zhi. Vocal cords diseases detection by multi-band nonlinear analysis of voice[J]. ACTA ACUSTICA, 2014, 39(1): 111-118. CSTR: 32049.14.11-2065.2014.01.013

嗓音多频带非线性分析的声带病变识别

基金项目: 

国家自然科学基金(61271359,61071215)

苏州大学捷美生物医学工程仪器联合实验室项目资助

详细信息
    通讯作者:

    陶智,Email:taoz@suda.edu.cn

Vocal cords diseases detection by multi-band nonlinear analysis of voice

  • 摘要: 提出了一种嗓音多频带非线性分析的声带病变识别方法,以提高声带病变嗓音的识别率。首先采用Gammatone听觉滤波器组对嗓音信号进行滤波,求取每个频带下的最大李雅普诺夫指数;对映射到核空间的数据采用高斯最大似然度准则优化核函数,然后采用优化核主成分分析算法实现特征抽取。识别实验表明,多频带最大李雅普诺夫指数的识别率比传统的MFCC和最大李雅普诺夫指数分别有6.52%和8.45%的提高,且采用优化核主成分分析算法比传统核主成分分析算法有更好的抽取效果.将多频带非线性分析和优化核主成分分析算法结合,识别率提升至97.82%。
    Abstract: In order to improve the recognition rate of pathological voices caused by disease of vocal cords, multi-band nonlinear analysis is proposed. Gammatone filter bank is applied to voice signal for front-end time-domain filtering, and then calculate the largest Lyapunov exponent of every band. Data is first mapped into kernel space and use Gaussian maximum likelihood rule to get the best parameter for kernel, which is used for kernel principal component analysis to extract feature. The proposed feature achieves higher recognition rate of 6.25% and 8.45% than MFCC and the largest Lyapunov exponent respectively. When the proposed kernel function is used for kernel principal component analysis, it achieves better performance than traditional function. Ultimately, we get recognition rate of 97.82% by combing them.
计量
  • 文章访问数:  50
  • HTML全文浏览量:  2
  • PDF下载量:  10
  • 被引次数: 0
出版历程
  • 收稿日期:  2012-09-20
  • 修回日期:  2013-03-18
  • 网络出版日期:  2022-06-27

目录

    /

    返回文章
    返回