This paper describes the development of a command-based robust speech recognition system for the Portuguese language. Due to an efficient noise reduction algorithm the system can be operated in adverse noise environments such as in vehicles or factories. The acquisition of a Portuguese database in the scope on the Tecnovoz project is addressed in this paper. The paper also addresses a new noise-robust front-end and some experiments regarding the best acoustic model to use for a command-based speech recognizer. The trade off between whole-word and phone models is discussed. Performance tests of the recognizer are presented.