Speech recognition for program control and data entry in a production environment

The Lister Hill National Center for Biomedical Communications, an R&D division of the National Library of Medicine, has developed a PC-based system for semi-automated entry of journal citation data into MEDLINE®. The system, called MARS for Medical Article Records System, includes many automated features but requires a few manual tasks such as scanning and the entry of certain data that are not located on the scanned page. Now that considerable computing power and speed are routinely available on desktop PCs, we think it may be possible to include speech recognition as an optional user interface to reduce operator burden and to improve speed and quality for document scanning and data entry. We undertook a study to determine if speech recognition was sufficiently accurate, reliable and immune to noise to warrant integration with MARS workstations. The study focussed on the suitability of both continuous and discrete speech recognition for computer program control and for data entry in a production environment. Following a carefully structured format, 20 participants tested continuous speech recognition and 20 participants tested discrete speech recognition in both a quiet and a noisy environment. Performance measures were accuracy and speed. Both continuous and discrete recognition were very accurate, fast and immune to noise when used for program control. For data entry, though discrete speech recognition was about 90% accurate, it was very slow. Continuous speech recognition was faster for data entry, but was only about 76% accurate. As a result of the study, speech recognition has been integrated into the MARS scan workstation for program control.