Use of automatic speech recognition: current and potential applications

Abstract

The development of more sophisticated techniques for analysing human speech combined with the increased processing power of microcomputers has resulted in improved performance for machine recognition of human utterances. Consequently, automatic speech recognisers are now either operational or being considered in a variety of industrial tasks, telecommunications, office and aerospace environments, and disabled user applications. However, take-up in two of these application areas, namely, in avionics on the aircraft flight deck, and for disabled users, has been slow. The issues surrounding this state of affairs are briefly discussed in this article, with conclusions being drawn on the way forward for these potential application areas.