The spectral analysis of heart valve sound is a noninvasive diagnostic method known to be useful in evaluating the state of the heart valve function. This may provide early detection of valve calcification, thrombus or destruction, since previous studies have shown that the dominant frequency peak moved to a high frequency area when natural heart valve leaflets were calcified, stiffened or destroyed. However, it is important for a heart valve sound diagnostic system to find a proper spectral analysis method on phonocardiography. Until now, conventional frequency analyses such as the Fourier transform or autoregressive spectral estimation technique have been used to estimate spectral components of a phonocardiogram, but they are inappropriate because the signal frequency is assumed to remain constant during the transform interval. To overcome this problem, in this study, FOS (Fast Orthogonal Search) & MUSIC (MUltiple SIgnal Classification), which both appeared suitable for the analysis of biological data, were applied to prosthetic heart valve sound as the new heart valve sound spectral analysis methods. Five subjects with normally functioning mechanical heart valves and a patient with a malfunctioning one were selected to collect the heart valve sound signals. As a result, the second dominant peak frequency proved to be important along with the first dominant peak frequency in identifying the valve function. This study showed that the new heart valve sound spectral analysis method presented in this paper may be an effective method in heart valve sound analysis. Further study using this system in a large population of patients will aid in providing a diagnostic method in the early detection of valve failure.