This paper describes a method of adapting a continuous density HMM recogniser trained on clean cepstral speech data to make it robust to noise. The technique is based on parallel model combination (PMC) in which the parameters of corresponding pairs of speech and noise states are combined to yield a set of compensated parameters. It improves on earlier cepstral mean compensation methods in that it also adapts the variances and as a result can deal with much lower SNRs. The PMC method is evaluated on the NOISEX-92 noise database and shown to work well down to 0 dB SNR and below for both stationary and non-stationary noises. Furthermore, for relatively constant noise conditions, there is no additional computational cost at run-time.