Although results show an average recognition of only 75%, it is possible that missing elements may be reconstructed more precisely. Time recording with automated speech recognition seems to be possible in emergency medical missions. Average recognition in the simulated emergency setting was 75%. The gender of speaker and the number of words in a sentence had no influence. Recognition became significantly worse (89.5% versus 82.3%, P<0.0001 ) when numbers had to be recognised. Nevertheless, the difference was not statistically significant.
Overall recognition was best for the PC with a headset (89%) followed by the pen-PC with a headset (85%), the PC with a microphone (84%) and the pen-PC with a microphone (80%). Two emergency physicians tested the system in a simulated emergency setting using the collar microphone and the pen-PC with an analogue wireless connection. Seven women and 15 men spoke a text with 29 phrases to be recognised. One was a standard headset that came with the recognition software, the other was a small microphone (Lavalier-Kondensatormikrofon EM 116 from Vivanco), that could be attached to the operators collar. On both computers two different microphones were tested. One was a stationary PC (500MHz Pentium III, 128MB RAM, Soundblaster PCI 128 Soundcard, Win NT 4.0), the other was a mobile pen-PC that had already proven its value during emergency missions (Fujitsu Stylistic 2300, 230Mhz MMX Processor, 160MB RAM, embedded soundcard ESS 1879 chipset, Win98 2nd ed.).
Standard speech recognition software (IBM ViaVoice 7.0) was adapted and installed on two different computer systems. A special erase programme for the documentation of all time events was developed. Automated speech recognition may offer a solution. All conventional methods of time recording are either too inaccurate or elaborate for routine application. Precise documentation of medical treatment in emergency medical missions and for resuscitation is essential from a medical, legal and quality assurance point of view.