Speech recognition in aircrafts can greatly simplify operation of equipment in both military and civil environments. This paper describes the development of specialized recognizers for two military applications: One for assisting a jet pilot wearing a breathing mask and another for a radar evaluator within an aircraft (similarly to AWACS). In both cases it is not practical to collect sufficient speech data under real conditions for a robust specialized recognizer. This paper describes two methods for overcoming this data problem and building a recognizer with minimal effort: retraining the baseline system with real application data and combining the baseline system with a new trained system. These methods greatly improved the performance of the baseline system (US English recognizer adapted to car environment).