Respiratory sounds, i.e. tracheal and lung sounds, have been of great interest due to their diagnostic values as well as the potential of their use in the estimation of the respiratory dynamics (mainly airflow). Thus the aim of the study is to present a new method to filter the heart sound interference from the tracheal sounds. Tracheal sounds and airflow signals were collected by using an accelerometer from 10 healthy subjects. Tracheal sounds were then pre-processed by Recursive Least Square - Adaptive Noise Cancellation (RLS-ANC) filter to remove background noise. Gabor time- frequency expansion was used for both heart sound localization and reduction problem. In the first step of filtering, RLS- ANC successfully filtered out the broad - band ambient noise. Reconstruction of tracheal sound was achieved from modified Gabor coefficients without heart sound noise. Visual inspection and quantitative analysis demonstrated that Gabor time-frequency masking with RLS-ANC filters provides successful tracheal sound signal separation.