Development of a Speech-Based Dialogue System for Report Dictation and Machine Control in the Endoscopic Laboratory

Background and Study Aims: Reporting and machine control based on speech technology can enhance work efficiency in the gastrointestinal endoscopy laboratory.

Materials and Methods: The status and activation of endoscopy laboratory equipment were described as a multivariate parameter and function system. Speech recognition, text evaluation and action definition engines were installed. Special programs were developed for the grammatical analysis of command sentences, and a rule-based expert system for the definition of machine answers. A speech backup engine provides feedback to the user. Techniques were applied based on the „Hidden Markov” model of discrete word, user-independent speech recognition and on phoneme-based speech synthesis. Speech samples were collected from three male low-tone investigators.

Results: The dictation module and machine control modules were incorporated in a personal computer (PC) simulation program. Altogether 100 unidentified patient records were analyzed. The sentences were grouped according to keywords, which indicate the main topics of a gastrointestinal endoscopy report. They were: „endoscope”, „esophagus”, „cardia”, „fundus”, „corpus”, „antrum”, „pylorus”, „bulbus”, and „postbulbar section”, in addition to the major pathological findings: „erosion”, „ulceration”, and „malignancy”. „Biopsy” and „diagnosis” were also included. We implemented wireless speech communication control commands for equipment including an endoscopy unit, video, monitor, printer, and PC. The recognition rate was 95 %.

Conclusions: Speech technology may soon become an integrated part of our daily routine in the endoscopy laboratory. A central speech and laboratory computer could be the most efficient alternative to having separate speech recognition units in all items of equipment.

References

• 1 Cohen P R, Oviatt S L. The role of voice input for human-machine communication.  Proc Natl Acad Sci USA. 1995;  92 9921-9927
• 2 Hersmann T. Speech recognition technology is becoming independent of speakers and languages.  Byte. 1997;  10 100-112
• 3 Jelinek F. Training and search methods for speech recognition.  Proc Natl Acad Sci USA. 1995;  92 9964-9969
• 4 Liberman M. Computer speech synthesis: its status and prospects.  Proc Natl Acad Sci USA. 1995;  92 9928-9931
• 5 Moore R C. Integration of speech with natural language understanding.  Proc Natl Acad Sci USA. 1995;  92 983-988
• 6 Grasso M A. Automated speech recognition in medical application.  MD Comput. 1995;  12 16-23
• 7 De Brujin L M, Verheijen E, Hasman A, et al. Speech interfacing for diagnosis reporting systems: an overview.  Comput Methods Programs Biomed. 1995;  48 151-157
• 8 Meier G A, Baak J P. Reporting by speech recognition.  Hum Pathol. 1995;  26 813-815
• 9 Ikehari H, Matumoto T, Linuma T A, et al. Analysis of bone scintigram data using speech recognition reporting system.  Med Informatics (London). 1993;  16 1-6
• 10 Imhoff M. Acquisition of ICU data: concepts and demands.  Int J Clin Monit Comput. 1992;  9 229-237
• 11 Dietz U, Rupprecht H J, Espinola-Klein C, Meyer J. Automatische Berichtschreibung in der Kardiologie mittels eines Spracherkennungssystems.  Z Kardiol. 1996;  85 684-688
• 12 Seelbach C. A perspective on early commercial applications of voice-processing technology for telecommunications and aids for the handicapped.  Proc Natl Acad Sci USA. 1995;  92 9989-9990
• 13 Johannes R S, Carr-Locke D L. The role of automated speech recognition in endoscopic data collection.  Endoscopy. 1992;  24 (Suppl. 2) 492-498
• 14 Makhoul J, Schwartz R. State of the art in continuous speech recognition.  Proc Natl Acad Sci USA. 1995;  92 9956-9963