Speech recognition, which remained on the fringes of commercial interest for many years, came into prominence recently due to the support extended to this research area by the Advanced Research Projects Agency of theusa. More recently, this area of research has received added impetus due to the priority assigned to the development of fifth generation computers by Japan and several other countries of the world and the importance of speech input/output systems therein. India has a long tradition of good quality work in this area. In this paper, we present a brief overview of different aspects of automatic speech recognition research and present the state-of-the art in this area. We cover the world trends in this area of research, with special attention to work done in India.