Automatic speech recognition has come a long way over the years, but its still not anywhere near what would be needed for the voice itself to replace the keyboard and the mouse. We all dream of being able to talk to our computers just like in Star Trek, but the dream still isn't here. Carnegie Mellon University's Rob A. Rutenbar is leading a national research team to develop a technology that could change all that. Working jointly with researchers at the University of California at Berkeley, the research team is working on a hardware automatic speech recognition solution that will move the task from software to silicon. The technology should be with us in two to three years.