A heart sound segmentation algorithm, which separates the heart sound signal into four parts: the first heart sound, the
systolic period, the second heart sound, and the diastolic period has been developed. The algorithm uses discrete wavelet decomposition and reconstruction to produce intensity envelopes of approximations and details of the original phonocardiographic signal. The performance of the algorithm has been evaluated using 1165 cardiac periods from 77 digital phonocardiographic recordings including normal and abnormal heart sounds. The algorithm has shown over 93 percent correct ratio.