Energy from wind turbines has enjoyed a remarkable growth worldwide in the past decades. In Canada, generation capacity has increased dramatically.  The issue of noise and wind turbines has become an issue of interest for researchers and acoustics practitioners. For utility scale wind turbines, broadband noise emanating from the trailing edge of the wind turbine blade is a large contributor to the overall noise emission. In order to minimize the noise impact, regulatory bodies often set limits to the noise level observed nearby. Good noise predictive tools are necessary to estimate noise emissions before a wind farm development. These tools are developed in this study from computational fluid dynamics studies such as Large Eddy Simulation (LES) in conjunction with the Ffowcs-Williams and Hawkings (FW–H) acoustic analogy to predict the far field sound.  These results are compared to those obtained through the use of semi-empirical prediction models.  Validation of these predictive tools are compared with experimental measurements of 2D airfoil self noise and with field measurements obtained at the University of Waterloo Wind Energy Research wind turbine field site. The developed predictive tools show good agreement with the measured experimental data leading to further development of the predictive tools.