Résumé
Auscultation [the interpretation by a physician of heart sounds] is a fundamental component in cardiac diagnosis. It is, however, a difficult skill to acquire. In this paper, we present study for a system Intended to aid in heart sound analysis and diagnosis based on detection of different events [main and additional sounds, murmurs and clicks] present in the cardiac cycle with resolution at the level of sampling period in time and in frequency at the level of FFT points used and for each event set of parameters in time and frequency domains have been extracted for normal and abnormal cases without using ECG signal as reference. These parameters could be easily used by the doctor for analyzing the extracted parameters for normal, mitralstenosis, and s2 split sounds have been extracted from recorded sounds