FDAI logo   ::  Site Map  ::   
Home  |  About This Website  |  Contact Us
Home » ... » Evidence from Resource

Evidence from Resource 15 pieces of evidence from this resource.

Barbato, G. (1999). Lessons learned: Integrating voice recognition and automation target cueing symbology for fighter attack. In R.S. Jensen, B. Cox, J.D. Callister, & R. Lavis (Eds.), Proceedings of the 10th International Symposium on Aviation Psychology, 203-207. Columbus, OH: The Ohio State University.

  1.  
  2. Evidence Type: Excerpt from Experiment
    Evidence: "Other tasks during the navigation segment in which the voice and manual interfaces were compared included: 1) correcting system malfunctions, and 2) changing radio frequency channels to place radio calls. For changing radio frequencies—a task similar in nature to rerouting in that a string of alphanumerics was entered into the simulator, the voice interface improved pilots’ speed and accuracy to accomplish the task compared to the manual interface (F [1,11] = 7.63, p < .05). However, the improvement was less than what the voice interface provided for the mission rerouting task. For one system malfunction—flight control pitch fault—voice and manual interfaces demonstrated no differences for accomplishing the pitch fault reset task; for another malfunction—Global Positioning System (GPS) failure—the voice interface increased the time to complete the GPS failure task compared to the manual interface. Possible reasons for these results will be explained in the discussion section."
    Issue: data entry and programming may be difficult and time consuming (Issue #112) See Issue details
    Strength: +3
    Aircraft: unspecified
    Equipment: automation

  3.  
  4. Evidence Type: Excerpt from Experiment
    Evidence: "During the weapon delivery segment for nine of the twelve pilots, the voice interface had an overall error rate of 3.9%. When the single-repeat deletion errors were removed from the data set, the adjusted overall mean error rate dropped to 1.9%. After removing subject two’s data, the largest sources of error during weapon delivery were substitutions and deletions. Although both types of error only occurred 0.4% of the time, it can still be accounted for. Closer examination of the data showed that the substitution errors occurred when designating multiple targets."
    Issue: programming may be susceptible to error (Issue #170) See Issue details
    Strength: +1
    Aircraft: unspecified
    Equipment: automation

  5.  
  6. Evidence Type: Excerpt from Experiment
    Evidence: "During the navigation segment for nine of the twelve pilots (voice recordings for data from three pilots were not available recorded due to tape machine malfunctionor tabulated), the overall voice interface error rate averaged 2.2%. Many of the errors were "single-repeat" deletion errors. These were resolved with a single repeat of the command. Most of these errors could have been avoided through more extensive voice template training, so another analysis was performed on an adjusted data set in which these errors were removed. This analysis revealed that, minus the single repeat errors, voice interface average error rate dropped to 0.6%."
    Issue: programming may be susceptible to error (Issue #170) See Issue details
    Strength: +1
    Aircraft: unspecified
    Equipment: automation

  7.  
  8. Evidence Type: Excerpt from Experiment
    Evidence: "Figure 10 illustrates the speech recognition error rates for weapon delivery. Insertions, deletions, and substitutions (see navigation segment for descriptions of these error types) are shown for nine of the twelve pilots. The voice interface had an overall error rate during weapon delivery of 3.9%."
    Issue: programming may be susceptible to error (Issue #170) See Issue details
    Strength: +1
    Aircraft: unspecified
    Equipment: automation

  9.  
  10. Evidence Type: Excerpt from Experiment
    Evidence: "Figure 7 illustrates the incidence of three types of speech recognition errors for the navigation segment: insertions, deletions, and substitutions. Insertions are errors where the voice system inserts commands that the pilot did not speak. Deletions are errors where the voice system did not recognize what the pilot correctly spoke and took no action. Substitutions are errors where the voice system misrecognized what the pilot spoke and executed the wrong command. The figure illustrates the voice interface error rate during the navigation segment for nine of the twelve pilots—data from three pilots were not recorded. The figure shows voice interface error rate overall averaged 2.2%."
    Issue: programming may be susceptible to error (Issue #170) See Issue details
    Strength: +1
    Aircraft: unspecified
    Equipment: automation

  11.  
  12. Evidence Type: Excerpt from Experiment
    Evidence: "The results verified the hypotheses and showed that the pilots were able to designate targets more quickly using voice control coupled with the ATC than with manual control coupled with the ATC (F [1,11] = 4.79, p < .05). Further, pilots reported a decrease in workload when using the voice versus manual interface in combination with the ATC (F [1,11] = 4.73, p < .05)."
    Issue: automation may adversely affect pilot workload (Issue #79) See Issue details
    Strength: -1
    Aircraft: unspecified
    Equipment: automation

  13.  
  14. Evidence Type: Excerpt from Experiment
    Evidence: "The results verified the hypotheses and showed that the pilots were able to designate targets more quickly using voice control coupled with the ATC than with manual control coupled with the ATC (F [1,11] = 4.79, p < .05). Further, pilots reported a decrease in workload when using the voice versus manual interface in combination with the ATC (F [1,11] = 4.73, p < .05)."
    Issue: data entry and programming may be difficult and time consuming (Issue #112) See Issue details
    Strength: -1
    Aircraft: unspecified
    Equipment: automation

  15.  
  16. Evidence Type: Excerpt from Experiment
    Evidence: "Results of the weapon delivery questionnaire data were consistent with the navigation segment questionnaire data. During weapon delivery, pilots rated the voice interface combined with the auto-target cue as most effective for identifying targets when compared to the manual or voice interfaces alone or the manual interface combined with ATC. For designating targets, pilots rated both control types effective regardless of whether or not ATC was used, but they rated their performance most effective and gave their highest ratings for the voice interface combined with ATC."
    Issue: automation performance may be limited (Issue #126) See Issue details
    Strength: -1
    Aircraft: unspecified
    Equipment: automation

  17.  
  18. Evidence Type: Excerpt from Experiment
    Evidence: "MANOVA results also showed a significant Control Type× ATC interaction for workload (F [1,11] = 4.73, p < .05). Post hoc tests showed that: 1) without ATC, Control Type had no effect on pilot workload, and 2) with ATC, average pilot workload ratings for using the voice interface were 22% lower (average rating = 46) than those for the manual interface (average rating = 59). The weapon delivery workload results are depicted in Figure 9 (next page)."
    Issue: automation may adversely affect pilot workload (Issue #79) See Issue details
    Strength: -1
    Aircraft: unspecified
    Equipment: automation

  19.  
  20. Evidence Type: Excerpt from Experiment
    Evidence: "Pilot questionnaire responses confirmed that the voice interface was significantly more effective in completing the mission reroute than the manual interface. The effectiveness scale ranged from 1 (Poor) to 5 (Very Good). Across pilots, the manual interface was rated as neither a hindrance nor an advantage for accomplishing the reroute task (average rating = 3.2). Across pilots, the voice interface was rated as highly effective for accomplishing the task (average rating = 4.8)."
    Issue: automation performance may be limited (Issue #126) See Issue details
    Strength: -2
    Aircraft: unspecified
    Equipment: automation

  21.  
  22. Evidence Type: Excerpt from Experiment
    Evidence: "In regard to workload during rerouting, there was a significant two-way interaction for Control Type× TF Task Load (F [1,11] = 4.84, p < .05). Post-hoc tests showed that: 1) during high TF Task Loading, when the voice interface was used to accomplish mission rerouting, it decreased pilot workload by 31% compared to using the manual interface, and 2) during low TF Task Loading, Control Type had no effect on rerouting. During high TF Task Loading, the pilots’ average SWAT ratings to reroute the mission dropped from a 39 with the manual interface to a 27 with the voice interface, whereas during low TF Task Loading, pilots’ average SWAT ratings remained virtually constant at 34."
    Issue: automation may adversely affect pilot workload (Issue #79) See Issue details
    Strength: -2
    Aircraft: unspecified
    Equipment: automation

  23.  
  24. Evidence Type: Excerpt from Experiment
    Evidence: "In regard to workload during rerouting, there was a significant two-way interaction for Control Type× TF Task Load (F [1,11] = 4.84, p < .05). Post-hoc tests showed that: 1) during high TF Task Loading, when the voice interface was used to accomplish mission rerouting, it decreased pilot workload by 31% compared to using the manual interface, and 2) during low TF Task Loading, Control Type had no effect on rerouting. During high TF Task Loading, the pilots’ average SWAT ratings to reroute the mission dropped from a 39 with the manual interface to a 27 with the voice interface, whereas during low TF Task Loading, pilots’ average SWAT ratings remained virtually constant at 34."
    Issue: automation may adversely affect pilot workload (Issue #79) See Issue details
    Strength: -2
    Aircraft: unspecified
    Equipment: automation

  25.  
  26. Evidence Type: Excerpt from Experiment
    Evidence: "Other tasks during the navigation segment in which the voice and manual interfaces were compared included: 1) correcting system malfunctions, and 2) changing radio frequency channels to place radio calls. For changing radio frequencies—a task similar in nature to rerouting in that a string of alphanumerics was entered into the simulator, the voice interface improved pilots’ speed and accuracy to accomplish the task compared to the manual interface (F [1,11] = 7.63, p < .05). However, the improvement was less than what the voice interface provided for the mission rerouting task. For one system malfunction—flight control pitch fault—voice and manual interfaces demonstrated no differences for accomplishing the pitch fault reset task; for another malfunction—Global Positioning System (GPS) failure—the voice interface increased the time to complete the GPS failure task compared to the manual interface. Possible reasons for these results will be explained in the discussion section."
    Issue: data entry and programming may be difficult and time consuming (Issue #112) See Issue details
    Strength: -3
    Aircraft: unspecified
    Equipment: automation

  27.  
  28. Evidence Type: Excerpt from Experiment
    Evidence: "Navigation Results. For the mission rerouting task, the main effect of Control Type was significant (F [1,11] = 6.77, p < .05). By using the voice interface, pilots completed the rerouting task almost 14 seconds quicker that when using the manual interface."
    Issue: data entry and programming may be difficult and time consuming (Issue #112) See Issue details
    Strength: -3
    Aircraft: unspecified
    Equipment: automation

  29.  
  30. Evidence Type: Excerpt from Experiment
    Evidence: "Summary. Navigation segment results showed that voice recognition significantly improved the speed and accuracy of pilot data input during re-route when compared to manual input. Weapon delivery segment results showed that pilot performance was significantly improved by integrating auto-target cueing features with voice recognition when compared to the manual, throttle-mounted switches. In fact, in all but one of the voice interface cases, pilots were able to correctly designate all six of the tanker aircraft in a single pass on the airfield at significantly greater distances from the airfield than when they used the manual interface."
    Issue: data entry and programming may be difficult and time consuming (Issue #112) See Issue details
    Strength: -3
    Aircraft: unspecified
    Equipment: automation
Flight Deck Automation Issues Website  
© 1997-2013 Research Integrations, Inc.