Heart Sound Localization and Reduction in Tracheal Sounds by Gabor Time-Frequency Masking

Background and aim: Respiratorysounds, i.e. tracheal and lung sounds, have been of great interest due to theirdiagnostic values as well as the potential of their use in the estimation ofthe respiratory dynamics (mainly airflow). Thus the aim of the study is topresent a new method to filter the heart sound interference from the trachealsounds. Materials and methods: Trachealsounds and airflow signals were collected by using an accelerometer from 10 healthysubjects. Tracheal sounds were then pre-processed by Recursive Least Square -Adaptive Noise Cancellation (RLS-ANC) filter to remove background noise. Gabortime-frequency expansion was used for both heart sound localization andreduction problem. Results: Inthe first step of filtering, RLS-ANC successfully filtered out the broad - bandambient noise. Reconstruction of tracheal sound was achieved from modifiedGabor coefficients without heart sound noise. Conclusion: Visual inspection and quantitative analysisdemonstrated that Gabor time-frequency masking with RLS-ANC filters provides successfultracheal sound signal separation.