For many reasons, speech is a convenient mean for a human to interact with a machine. Computer speech recognition (or automatic speech recognition, ASR) is the process of converting the message uttered by a person into a sequence of words. In spite of all technological advances made in the field of ASR, due to many factors that influence the recognition rate, speech recognition is still a challenging research area. In this paper, the author presents two speech recognition systems for Romanian language, one based on statistical methods, hidden Markov models, and the other one based on dynamic time warping. The systems were tested for a set of voice commands applied to control electronic devices.