VOICE RECOGNITION IN RADIOLOGY REPORTING

OBJECTIVE. Recent advances in computer hardware and software technolog y have improved voice recognition systems used for radiology reporting . We describe and analyze this technology and some of its costs as wel l as the prospects for using voice recognition systems in the transcri ption of radiology reports. Factors to be considered in choosing a sys tem include language model, speech flow, vocabulary size, and methods of acoustic modeling. CONCLUSION. Careful evaluation of individual rad iology practices will permit proper introduction of voice recognition technology into mainstream clinical use. With this new technology, rad iologists can use normal speech patterns to dictate while reviewing fi lms. Also, this technology can use standard personal computers to redu ce hardware costs to a level acceptable to radiology departments.