The Gabor expansion is a mathematical tool, which provides a joint time-frequency representation of a given signal by decomposing it into time-frequency elementary signals called Gabor atoms. It has been used in a variety of signal processing applications, including biomedical signal processing. In this paper we present a time-frequency masking technique based on Gabor expansion for both heart sound localization and reduction problem. Gabor coefficients of lung sound segments recorded from trachea are calculated and masked to remove the distinctive heart sound effects. Reconstruction of lung sound is achieved from modified Gabor coefficients without heart sound noise.