For the most part, speech recognition technology has been lousy. Well, with this fact in mind, a group of universities are working on a chip designed to allow speech reconigition to be more accessbile. The chip will be totally dedicated to the task of speech recognition.

According to this news release from Carnegie Mellon University (CMU), the National Science Foundation awarded a $1 million grant to a team of CMU and researchers at the University of California at Berkeley to develop a silicon chip for automatic speech recognition. In fact, speech recognition will move from software to hardware. The goal of the engineers is to develop “a radically new and efficient silicon chip architecture that only does speech recognition, but does this 100 to 1,000 times more efficiently than a conventional computer.” Even if the future chips will be integrated in cell phones or PDAs, the real goal is to help security and emergency organizations. These chips should be ready in three years.