Improving the performance of cough sound discriminator in reverberant environments using microphone array

In this paper, the performance of a cough sound discriminator capable of distinguishing between dry and wet cough sounds is evaluated in reverberant environments. In addition, microphone array is used in order to improve the performance of the cough sound discriminator. Cough sounds were acquired by a single microphone in a reverberant room at various microphone-to-speaker distances. Results showed a decrease in the performance of the cough sound discriminator as the distance between the microphone and speaker increased. In order to improve the performance of the cough sound discriminator, a microphone array structure of up to seven microphones was used. The linear separation score measured for numerous microphone-to-microphone and microphone-to-speaker distances revealed a significant improvement in the performance of the cough sound discriminator using the microphone array.