Using your voice: speech recognition technology in medicine and surgery.

Data entry and control of equipment are existing applications of speech recognition technology in medicine and surgery. Specialized dictation tasks, such as radiographic reporting, are feasible using isolated speech, speaker dependent, large vocabulary devices. General dictation will be possible using an automatic dictation device. Vocabulary size varies from a few to many thousand words, but most data entry, command, and control applications require 200 words or less, whereas specialized dictation tasks require about 1000 words and general dictation for a given user requires on the order of 10,000 words.