基于高频子带特征的咳嗽检测方法

被引:1
作者
陈冲 [1 ]
尤鸣宇 [1 ]
刘家铭 [1 ]
王峥 [1 ]
李国正 [1 ]
徐镶怀 [2 ]
邱忠民 [2 ]
机构
[1] 同济大学控制科学与工程系
[2] 同济大学附属同济医院呼吸内科
关键词
子带; 咳嗽检测; 特征提取; gammatone滤波器组; 模式识别;
D O I
10.13232/j.cnki.jnju.2015.01.022
中图分类号
TN912.34 [语音识别与设备]; R56 [呼吸系及胸部疾病];
学科分类号
摘要
咳嗽是呼吸道疾病中一种常见的症状,基于模式识别算法可以对语音信号中咳嗽对象的频度和强度进行客观化分析,进而帮助临床咳嗽的诊断及病程跟踪.在临床录制的连续语音信号中检测出咳嗽对象是咳嗽诊断及分析的基础.本文将咳嗽检测视为模式识别中的二分类问题,借助于分类器将咳嗽对象从背景信号中分离.在深入研究咳嗽频谱分布的基础上,提出一种新的基于高频子带的特征提取方法(High-frequency subband features method),在提取咳嗽信号特征之前,使用高频滤波器获取高频部分信号.在合成实验数据的过程中使用了不同的噪声类型和信噪比来组成不同的实验环境,并且在每种实验环境下对几种特征提取方法进行了评价与分析.实验结果表明,相比于常见的语音信号特征,结合基于高频子带特征的咳嗽检测方法在检测正确率等性能指标上有显著地提升.
引用
收藏
页码:157 / 164
页数:8
相关论文
共 17 条
[1]  
"PLP and RASTA (and MFCC,and inversion)in Matlab,". D.P.W.Ellis. http://www.ee.columbia.edu/dpwe/resources/matlab/rastamat/ . 2005
[2]  
Robust speaker identification using auditory features and computational auditory scene analysis. Yang Shao,DeLiang Wang. IEEE International Conference on Acoustics, Speech,and Signal Processing . 2008
[3]  
LIBSVM: A Library for support vector machines. Chang, Chih-Chung,Lin, Chih-Jen. ACM Transactions on Intelligent Systems and Technology . 2011
[4]  
Towards Generalizing Classification Based Speech Separation. Kun Han,DeLiang Wang. Audio, Speech, and Language Processing, IEEE Transactions on . 2013
[5]  
ERS guidelines on the assessment of cough. Morice A H,Fontana G A,Belvisi M G,Birring S S,Chung K F,Dicpinigaitis P V,Kastelik J A,McGarvey L P,Smith J A,Tatar M,Widdicombe J. The European respiratory journal : official journal of the European Society for Clinical Respiratory Physiology . 2007
[6]  
Detection of cough signals in continuous audio recordings using hidden Markov models. Matos Sergio,Birring Surinder S,Pavord Ian D,Evans David H. IEEE transactions on bio-medical engineering . 2006
[7]  
Cough signal recognition with gammatonecepstralcoefficients. Liu J M,You M Y,Li G Z,et al. 2013IEEE China Summit International Conference on Signal and Information . 2013
[8]  
Objective study of sensor relevance for automatic cough detection. DrugmanT,Ubrain J,Bauwens N,et al. IEEE Journal of Biomedical and Health Informatics . 2013
[9]  
Sound Event Recognition With Probabilistic Distance SVMs. Huy Dat TranHaizhou Li. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING . 2011
[10]  
A supervised learning approach to monaural segregation of reverberant speech. Jin Z.,Wang D. IEEE Transactions on Audio, Speech and Language Processing . 2009