Cough sound discrimination in noisy environments using microphone array

Cough sound discriminator algorithms are capable of distinguishing between dry and wet cough types. The performance of such algorithms, however, is affected by noise and reverberation in the environment. The effect of reverberation on the performance of cough sound discriminators was previously studied in [1]. In this paper, the effect of noise on the performance of cough sound discriminator is studied and quantitatively measured using previously defined Linear Separation Score (LSS) [1]. Experiments revealed a significant decrease in the performance of cough sound discriminator in the presence of white noise using a single microphone for cough sound acquisition. A microphone array structure containing a maximum of 7 microphones along with delay-and-sum beamforming algorithm was used to improve the performance of the cough sound discriminator. Experimental results showed improvement in the performance of the cough sound discriminator in the presence of white noise using microphone arrays.