Separation of crackles and squawks from vesicular sounds using a wavelet-based filtering technique

An automated way of revealing the diagnostic character of discontinuous adventitious sounds (DAS), i.e. crackles and squawks, by isolating them from vesicular sounds (VS), based on their nonstationarity, is presented in this paper. The proposed algorithm combines multiresolution analysis with hard thresholding in order to compose a wavelet-based stationary-non-stationary filter (WTST-NST). Applying the WTST-NST filter to fine/coarse crackles and squawks, selected from three lung sound databases, the coherent structure of the DAS is revealed and they are separated from VS. When compared to other separation tools, in noiseless case, the WTST-NST filter performed more accurately, objectively, and with lower computational cost. Owing to its simple implementation it can easily be used in clinical medicine.