This thesis presents two main approaches to estimating the spectral density of a stationary time series, that are based on the classical periodogram. Both of these are related to the non-parametric density estimation. One is the kernel spectral density estimator while the other one is the Bernstein polynomial spectral density estimator. We have also introduced the method to determine the optimal smoothing parameters for estimating the spectral density of a stationary zero-mean process. Finally, the thesis concludes with a simulation study in order to examine the finite sample properties of the proposed spectral density estimators.