Of all the tasks that make up a police officer’s skill set, report writing may be the dreariest. The maturation of speech recognition technology may help alleviate some of the drudgery that goes with creating written documentation of arrests, crimes and other on-duty incidents. At the same time, that technology helps accelerate data collection and document creation for police officers while improving the detail and accuracy of reports.
Mature technology
Personal computers have had speech recognition applications available for well over 20 years, but they were mostly not ready for prime time. Prone to recognition errors and difficult to navigate, most people who used speech recognition were those who had no other choice, such as the handicapped and workers whose hands were otherwise occupied when they needed to record something.
The advancement of the technology has become more apparent in handheld devices and voice-controlled assistants for the home, like Google Home and Amazon Echo. Where trying to get a verbal command to a computer to execute properly used to be a bad joke (“Open the pod bay door, Hal”), it’s now easier to put an appointment into your phone by saying something like, “Siri, set a dentist appointment for August 1 at 2 PM” than it is to enter it with a keyboard.
Efficiency and officer safety
Cops are taught that, if it’s not in the report, it didn’t happen. Still, the complexity of some incidents, and plain old fatigue, has resulted in critical details being left out of reports, often to the detriment of the case, or the officer’s career.
Accurate reports can go a long way toward quickly and effectively resolving cases.
By using their voice to dictate their reports, officers and other first responders can capture their notes as soon as an incident is concluded, when those important details that can ultimately impact a courtroom decision are still fresh in their minds. When including this extra detail is no more difficult than narrating it into the speech recognition system, the reports tend to be more complete and even more comprehensible.
The utility of speech recognition is also handy for situations where the officer is juggling other tasks. When I was a crime scene investigator, I had to document every photo I took (using a traditional film camera, because this was a long time ago), and often resorted to dictating the photo descriptions into a pocket tape recorder, to be transcribed into my report later. Had I used a smartphone or was able to import a digital sound file into the speech recognition system, I would have saved a lot of time.
Being able to dictate reports can also contribute to officer safety. Many agencies encourage officers to complete reports in the field, usually typing them into car-mounted laptops. This usually makes for some back-cramping ergonomics, but it also causes the officer to lose situational awareness. It’s easy to get buried in the composition of the report, staring at the laptop screen, and not keeping an eye on what’s going on outside the car. With a speech recognition system, officers can keep their heads up, watch what’s happening around them, and still complete the report faster than if they were typing everything.
Acclimation
Transitioning to a speech recognition system will require some training and adaptation. Most of us have produced written documents via a keyboard for most of our adult lives, and moving immediately to a speech interface requires some acclimation. There is also a learning curve with formatting and basic computer commands such as open, save, close, copy and paste, as well with navigating within a document for editing purposes.
However, most of learned how to type (even if we do it with only two fingers), and that was a far less natural interface than simply speaking what we needed to say. Now that the technology is sufficiently user-friendly, it’s time to consider moving to it.
