Speech Recognition 2007

As providers seek to offset the shortage of qualified medical transcriptionists, reduce the overall cost of transcription, decrease turnaround time, reduce dependence on external medical transcription outsourcing organizations (MTSOs), support the increasing volume of medical reports, facilitate increasingly geographically decentralized care delivery and supply input to the evolving electronic medical record, speech recognition is seen as an enabling technology.

At a time when there is a shortage of qualified medical transcriptionists and an increasing volume of medical reports, many providers are beginning to look to speech recognition technology as a means of managing the reporting and paper distribution bottleneck in the delivery system and facilitating the implementation of the electronic medical record. Some healthcare providers have even noted hundreds of thousands of dollars saved each year by going to speech recognition in addition to many instances of overall improved efficiency.

This report illustrates how well the vendors are performing overall including detailed areas covering accuracy, clinician/staff acceptance, quantifiable benefits, missing functionality, provider advice, etc.

A total of 11 vendors and 14 products are included in today’s study, including:

• Agfa TalkStation
• Commissure RadWhere Suite
• Crescendo Speech Processing
• Dolbey Fusion Speech
• eScription EditScript
• MedQuist SpeechQ
• Nuance Dragon NaturallySpeaking
• Nuance EXSpeech (Dictaphone)
• Nuance PowerScribe (Dictaphone)
• Provox VoxEnterprise
• SoftMed Speech Recognition (Back-End)
• SoftMed Speech Recognition (Front-End)
• StructuRad Speech Recognition