Future combat aircraft using speech recognition in the cockpit interface will also use positive pressure breathing (PPB) to allow operation at high G levels. This paper describes work which extends the n-tube model of vowel production to include intra-oral pressure. The aim is to improve speech recogniser performance under these conditions. An 8-tube DRM model was used, with the assumption of uniform compliance in all regions of the vocal tract. A side branch was added to simulate the oesophagus. The model shows that as the pressure is increased, the vowel space in the F1/F2 plane shrinks towards the region of F1 = 400 Hz, F2 = 1200 Hz. Measurements made on real speech show a similar trend, but the reduction in the range of F2 is less than that predicted by the model, probably as a result of variation of compliance in different areas of the vocal tract.