Speech recognition in the secondary school classroom: an exploratory study

Abstract Voice recognition software has improved dramatically over the past two or three years in terms of accuracy and usability and, at the same time, the costs of the software have been reduced significantly. While dictation software has so far been used predominantly in the medical and legal professions, it has been suggested that the software may benefit schoolchildren who have difficulties with spelling and writing. This paper reports on an exploratory study in which a group of second year secondary school pupils with reading ages ranging from 8.3 to 12.9 performed a set of tasks using the IBM VoiceType dictation package. The tasks involved normal classroom dictation by a teacher, the use of the keyboard to input the same text, the use of the dictation software to dictate the text to the computer, and the use of the dictation software to write a story based on a set of pictures. The results showed that the children could input text more quickly using voice dictation compared with keyboard entry, and that accuracy was acceptable and improving with practice. The implications of these findings for the use of dictation software in the classroom are discussed alongwith some directions for further research.