Cardiac auscultation has proven to be an excellent diagnostic tool. Heart sound processing algorithms are not completely robust in the presence of noise, requiring clean segments of heart sounds to extract reliable diagnostic features. This paper presents a new approach to detect transient noises mixed with heart sound. The algorithm explores a single channel source separation algorithm and evaluates the non-stationary separated signals. It has the potential to be applied in real-time. Using a database of heart sounds acquired in real-life scenario, the method showed a sensitivity and a specificity of 93.6% and 92.3%, respectively.