Cough signal recognition with Gammatone Cepstral Coefficients

Author

Jia-Ming Liu ; Mingyu You ; Guo-Zheng Li ; Zheng Wang ; Xianghuai Xu ; Zhongmin Qiu ; Wenjia Xie ; Chao An ; Sili Chen

Author_Institution

Dept. of Control Sci. & Eng., Tongji Univ., Shanghai, China

fYear

2013

fDate

6-10 July 2013

Firstpage

160

Lastpage

164

Abstract

Cough Recognition is a valuable classification problem in healthcare. Generally, feature representation contributes a lot to the overall classifying performance. In this paper, a novel feature extraction method, Gammatone Cepstral Coefficients (GTCC), is investigated for cough recognition. The accuracy of GTCC comparing with MFCC is evaluated on a designed cough dataset following a 10 fold cross-validation schemes. Considering the imbalance of that dataset, weighted SVM is applied as the base classifier. The results indicate that GTCC surpass MFCC in modeling cough signals. With combination of GTCC and MFCC, a better performance is achieved. This paper provides a better feature representation prototype in cough recognition.

Keywords

audio signal processing; diseases; feature extraction; health care; medical signal detection; signal classification; support vector machines; GTCC; MFCC; classification problem; cough signal recognition; cross-validation schemes; feature extraction; feature representation; gammatone cepstral coefficient; healthcare; weighted SVM; Accuracy; Diseases; Feature extraction; Filter banks; Mel frequency cepstral coefficient; Cough recognition; feature extraction; gammatone cepstral coefficients; gammatone filterbank;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal and Information Processing (ChinaSIP), 2013 IEEE China Summit & International Conference on

Conference_Location

Beijing

Type

conf

DOI

10.1109/ChinaSIP.2013.6625319

Filename

6625319