Voice controlled Aircraft - the next generation of aviation?

All of you may be quite familiar with voice recognition technology in computers, and may have even used them in dictating word documents and reports. But now this technology is increasingly being used to aid pilots in aircraft control , and thus , reducing their pilot workload.

The initial steps in this direction are being taken in Military aviation by companies like QinetiQ ( The same company which flew the Zephyr. See my earlier post http://airbornegeeks.blogspot.com/2011/02/aircraft-flying-for-5-years-without.html ) in the UK.  Designed to alleviate the problem of pilots spending too much time looking inside the cockpit – a problem exacerbated by the advent of complex multi-function displays – QinetiQ's Direct Voice Input (DVI) system incorporates speech recognition technology to facilitate the direct voice control of avionics equipment using standard aircrew helmet microphones and intercom.

The system is speaker independent, meaning that it does not need to be trained to recognize a specific user, unlike your microsoft voice recognition software ( which you have to "train" for a few minutes , before it can accept voice commands from you). It gives aircrew the ability to control aircraft systems using voice commands and access information without removing their hands from the flight controls or being distracted from what’s happening outside the aircraft.

The system addresses the demands on pilots presented by an increasing amount of technology in modern aircraft cockpits. Too much of a pilot's time can be spent looking "head-in" rather than "head-out" during sorties due to the advent of multi-function displays with menu structures many tiers deep. You can see this image - the cockpit of the F-22 Raptor to get an idea of how difficult it is.

In a lot of cockpits, much of the information is buried in nested menus that require the pilot to select numerous buttons to get to the information he needs. Voice allows you to just ask for this information say " show fuel status”.

Much of the heads down activity is not to read information it is to enter commands such as radio frequencies selection, weapons targeting, transponder settings.
Additionally, flying a helicopter requires to have one hand on the collective and one on the joystick, reaching out to select buttons means taking your hands of the flight controls. Doing this at low level and in bad visibility can be dangerous.

QinetiQ's system means is particularly important for single pilot operations or where one pilot is flying and another is performing a tactical role.According to the company ,
"DVI has now amassed more than 30 hours of MOD-funded flight trials with command recognition rates in excess of 90 per cent for all users providing effective speech control of non-safety critical avionic functions. The trials have included both Chinook and Gazelle helicopters and involved aircrew from all three UK services" 

The Eurofighter Typhoon currently in service with the UK RAF employs a speaker-dependent system, i.e. it requires each pilot to create a template ( much similar to the Microsoft speech software mentioned earlier) . The system is not used for any safety critical or weapon critical tasks, such as weapon release or lowering of the undercarriage, but is used for a wide range of other cockpit functions. Voice commands are confirmed by visual and/or aural feedback. The system is seen as a major design feature in the reduction of pilot workload, and even allows the pilot to assign targets to himself with two simple voice commands or to any of his wing-men with only five commands. 

Though the Technology looks very optimistic, there are some hurdles which it may have to overcome to become a commercial reality ,atleast in Military aircraft. Studies with pilots flying the JAS-39 Gripen have shown the quality of voice recognition reduced at high speeds , especially when the G- Force increases. In a helicopter, the speed is not an issue, but the rotor "noise" is. the sound from the rotors can impair the recognition power of the software, unless corrective noise cancellation methods are employed. A recognition accuracy of over 95 % is required for safe flight.

As of now, scientists are using Voice control in airplane cockpits with a guarded approach, but yet, fully convinced of its future efficacy.Current research gives us the hope that this could be reality in civilian planes in lesser than 5 years.