Cough detection using speech analysis

Common cold is a common disease now-a-days. Due to common cold patient faces cough, sore throat, sneezing and runny nose problem. Most of the time patients' speech sounds different due to cough. In this paper, analyzing speech recording of cough and normal state of a person, we have derived two sets of representative features. These features are used for classifying normal and cough state of the patient. The classification algorithms we have used are Support Vector Machine, Bayesian Classifier and Neural Network. On the generated real life dataset, we have applied the features and classifiers. We have listed the performance statistics of the exhaustive experiment. The performance measures reveal that the classifiers with the second feature set provide very good accuracy (greater than 70% for all the classifiers). Among the three classifiers Bayesian provides the best accuracy (86.31%).