FOCUS: New Technology Trends
40
Journal of Healthcare Information Management — Vol. 18, No. 4
Introduction
Continuous speech recognition entails the entry of full
documents in a professional business setting. In contrast,
discrete SRT is the entry of short voice commands to trigger
an immediate response from the computer. Discrete SRT is
more characteristic of telephone responses and older
speech recognition applications. Discrete SRT has become
more successful because it is easier to implement than
continuous SRT. Throughout the remainder of this paper,
the abbreviation “SRT” will refer to continuous SRT.
The success of speech recognition technology may
depend on many interrelated factors, including the degree
of computer expertise, the quality of computer software and
hardware, the physical environment, and the degree of
integration with the current application.1,2 Because of the
high costs of transcription and the need for specialized
vocabularies, the primary application of SRT (and the focus
of this paper) has been to healthcare. There are, however,
many potential applications to other fields as well.
The first section justifies the importance of the topic and
Harrison D. Green, PhD
A B S T R A C T
Continuous Speech Recognition Technology implementation is expensive, and the failure of
leading companies in this niche can hamper usefulness. C-SRT, if deployed and used with
speech macros, experiences vastly improved implementations and drastically reduces
medical transcription costs.A speech macro is a short phrase that is automatically translated
into a block of text or a graphic display.A more powerful form of speech macro can bring up
predefined templates and insert spoken text into the proper position automatically, based on
its interpretation. Cases from the author’s consulting experiences and from medical journals
emphasize the need for speech macros from a cost-benefit standpoint.A prototype program is
introduced that facilitates the process of creating macros.The need for macro management
software is r