南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (1): 157164.
陈 冲1,尤鸣宇1*,刘家铭1,王 铮1,李国正1,徐镶怀2,邱忠民2
Chen Chong1, You Mingyu1*, Liu Jiaming1, Wang Zheng1, Li Guozheng1, Xu Xianghuai2,Qiu Zhongmin2
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。
[1] Morice A H, Fontana G A, Belvisi M G, et al. ERS guidelines on the assessment of cough. European Respiratory Journal, 2007, 29(6): 1256~1276. [2] Matos S, Birring S S, Pavord I D. Detection of cough signals in continuous audio recordings using hidden Markov models. IEEE Transactions on Biomedical Engineering,2006, 53(6): 1078~1083. [3] Matos S, Birring S S, Pavord I D, et al. An automated system for 24-h monitoring of cough frequency: The leicestercough monitor. IEEE Transactions on Biomedical Engineering,2007, 54(8):1472~1478. [4] Shin S H, Hashimoto T,Hatano S. Automatic detection system for cough sounds as a symptom of abnormal health condition. IEEE Transactions on Information Technology in Biomedicine,2009, 13(4):486~493. [5] DrugmanT,Ubrain J,Bauwens N, et al. Objective study of sensor relevance for automatic cough detection. IEEE Journal of Biomedical and Health Informatics,2013, 17(3):699~707. [6] Jin Z Z, Wang D L. A supervised learning approach to monaural segregation of reverberant speech. IEEE Transactions on Audio, Speech, and Language Processing,2009, 17(4):625~638. [7] Hu G, Wang D L. A Tandem algorithm for pitch estimation and voiced speech segregation. IEEE Transactions on Audio, Speech, and Language Processing,2010, 18(8):2067~2079. [8] Wang Y X, Han K, Wang D L. Exploring monaural features for classification-based speech segregation. IEEE Transactions on Audio, Speech, and Language Processing,2013, 21(2):270~279. [9] Wang Y X, Wang D L. Towardsscaling up classification-based speech separation. IEEE Transactions on Audio, Speech, and Language Processing,2013, 21(7):1381~1390. [10] Tran H D, Li H Z. Sound event recognition with probabilistic distance SVMs. IEEE Transactions on Audio, Speech, and Language Processing,2011, 19(6):1556~1568. [11] Ye J, Kobayashi T, Murakawa M, et al. Kernel discriminant analysis for environmental sound recognition based on acoustic subspace. In: Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing,New York: IEEE Press, 2013:808~812. [12] Ellis D. PLP and RASTA (and MFCC, and Inversion) in Matlab.http://www.ee.columbia.edu/dpwe/resources/matlab/rastamat/.2005. [13] Shao Y, Wang D L.Robust speaker identification using auditory features and computational auditory scene analysis. In: Proceedings of 2008 IEEE International Conference on Acoustics, Speech and Signal Processing. New York: IEEE Press, 2008:1589~1592. [14] Liu J M, You M Y, Li G Z, et al. Cough signal recognition with gammatonecepstralcoefficients.2013 IEEE China Summit International Conference on Signal and Information, 2013: 160~164. [15] Chang, Chung C, Lin C J. A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2011, 2:1~27. http: //www.csie.ntu.edu.tw/~cjlin/libsvm. |
No related articles found! |
|