A case study in designing speech interaction with a patient monitor

Objective. New developments in speech interaction technology warrant the as sumption that some of the interaction problems at anesthesia workplaces can be solved using speech interaction. One application might be the documenta tion of the anesthetic procedure. Method. To investigate this hypothesis, a speech input system was developed for a commercially available patient mon itor (Datex-Ohmeda AS/3(TM) Anesthesia Monitor with Record-Keeper(TM)), whi ch in addition to standard functions also facilitates the generation of the anesthesia record. The speech input system was based on the IBM ViaVoice(T M) speech recognition technology (version Millennium Pro(TM)). The speech i nput device was preliminarily tested by 5 anesthetists wearing surgical mas ks under laboratory conditions and through retrospectively documenting 4 to 5 anesthetic procedures (each 12 to 17 documentation entries) in a calm si tuation. The speech interactive documentation procedure was compared with t he conventional keyboard documentation procedure. Results. The test persons achieved an overall word recognition rate between 72% and 92.4%. Between 7 6.5% and 97.7% of the single word commands could be completed without any c orrections. The same qualifier held for 58.5% to 86.3% of the two- and thre e-word commands. Despite high speech recognition error rates, almost all do cumentation entries (236 of 238) could be finished using speech interaction . Comparing both documentation techniques, speech interaction was said to b e more intuitive and caused less frustration than the keyboard documentatio n procedure. However, speech interactive documentation was rated less contr ollable because of the high speech recognition error rates and because the auditive feedback dialogues took too long. Conclusions. Modern speech recog nition tools are still not advanced enough to facilitate the design of appl ications with an almost natural speech interface and widespread user accept ance. Nevertheless, many tasks in anesthesia have the necessary characteris tics to be optimally supported by speech interaction. In contrast to earlie r approaches to speech-interactive anesthesia workplaces, successful applic ation today depends on the question of design rather than solely on that of technology. Many of the constraints and drawbacks of current technology ca n be overcome through appropriate design measures. The goals must focus fir st on identifying task areas in intensive care where speech interaction can yield real benefit in terms of work efficiency, and second on developing a nd evaluating an ergonomic design of speech interaction. The intended users seem to look forward to the incorporation of speech interaction at the wor kplace.