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
M.D. B. Molnar
II. Dept. of Medicine Semmelweis University
1088 Szentkirályi Street 46
Budapest
Hungary
Phone: +36-1-2660816
Email: mb@bel2.sote.hu
