Foetal phonocardiography (fPCG) is a non-invasive, cost-effective and simple technique for antenatal care. The fPCG signals contain vital information of diagnostic importance regarding the foetal health. However, the fPCG signal is usually contaminated by various noises and thus requires robust signal processing to denoise the signal. The main aim of this paper is to develop a methodology for removal of unwanted noise from the fPCG signal. The proposed methodology utilizes the non-negative matrix factorization (NMF) algorithm. The developed methodology is tested on both simulated and real-time fPCG signals. The performance of the developed methodology has been evaluated in terms of the gain in signal-to-noise ratio (SNR) achieved through the process of denoising. In particular, using the NMF algorithm, a substantial improvement in SNR of the fPCG signals in the range of 12-30 dB has been achieved, providing a high quality assessment of foetal well-being. © 2012 Informa UK, Ltd.