This paper first describes the AM-FM demodulation of an arterial pressure signal. Although it is known to be efficient on signals modulated by breathing, we demonstrate that in case of lack of respiratory modulation (central sleep apnea), the AM-FM algorithm doesn't perform well in heart rate extraction. We introduce then a new algorithm based on Singular Spectrum Analysis eigen values which performs better cardiac frequency estimation in this context. The error for cardiac frequency estimation is around 0.2 BPM (Beats Per Minute) versus 5.5 BPM for the AM-FM demodulation. Further experimentations will be performed (with this time both cardiac and respiratory assessments) and will deal with real sleep apnea cases.