As part of its mission to support the identification and integration of existing and emerging technologies, the Department of Homeland Security (DHS) Science and Technology Directorate (S&T) partnered with the Johns Hopkins University Applied Physics Laboratory (APL) and their sub-contractor Think-A-Move to develop Automated Speech Recognition (ASR) technology.
The resulting innovation is known as the Direct Artificial Intelligence System Interface, or DAISI, which enables voice-activated capabilities in noisy operational environments. DAISI was selected out of multiple prototypes developed in response to an April 2018 request for proposals.
Current speech recognition systems work reasonably well in quiet conditions, but quickly fail when the surrounding background noise increases—as is common for first responder situations. Being able to effectively communicate while multitasking, no matter the situation, will enhance situational awareness.
“S&T consistently supports the development of technologies that make first responders safer, enable accurate and timely sharing of data and critical information, and seamlessly integrate across platforms and jurisdictions,” said S&T Project Manager Cuong Luu. “DAISI addresses a need identified as a priority capability for responders—effective and reliable hands-free communication so they can focus on doing their job.”
Numerous Capabilities Within Easy Reach
DAISI is able to assist with various tasks throughout all stages of a response. While en route to an incident, the system provides voice control for the mobile data terminal, which is the computerized device used to communicate with the central dispatch office. Responders can use DAISI to initiate navigation, answer address queries, provide alternate routes, and pan and zoom throughout the map—all without lifting a finger.
Once they arrive safely at the incident, voice-enabled hydrant location queries and friction loss calculation (which impacts the amount of water pressure required by the fire hose) can save crucial time. DAISI is also able to instantly access WISER (Wireless Information System for Emergency Responders) to identify hazardous materials at the site and guide appropriate precautionary measures.
In addition to all these capabilities, on-scene report logging and transcription to text make capturing key benchmarks on the scene fast and easy. Back at the station, responders are able to use the event log to make the after-fire critique and fire investigation report more comprehensive and thorough.
Tech That Will Come in Handy for First Responders
Maryland’s Howard County Department of Fire & Rescue Services has served as a testbed for the DAISI prototype over the last three years. The crew there has put DAISI to the test, trying out use cases identified during development and validating more than 80 different requirements to meets the needs of all sorts of potential situations. For example, should the worst happen—perhaps a partial building collapse traps a crew member—voice-activated mayday alerts add reliable backup support when a responder needs assistance.
According to Howard County Battalion Chief Stanley Wurzburger, “DAISI quite literally can make the worst day of a firefighter’s career a little bit easier to get through.”
The Future of Hands-Free Comms
What truly sets DAISI apart from existing technologies is the sophisticated machine learning voice recognition capability. As APL Project Manager Julee Rendon puts it, “It’s really about the language processing, the acoustic modeling, and the noise filtering.”
Continued algorithm development is planned to ensure the platform will remain below the industry standard of a 15% word-error rate. The team also plans to explore ease-of-use for the user interface and long-term durability of the computer central processing unit to ensure DAISI’s ability to overcome the technical challenge of resource limitation.
Commercial smart devices that can be similarly called upon by name and tasked with a multitude of requests require substantial connectivity, processing power, and battery life. DAISI is being designed for high performance regardless of the situation so function won’t be compromised by remote locations or extended use.
“We’re looking at how to minimize the resource consumption and find the sweet spot of a capability like this that has to be available to first responders who may not have that bench of resources that they can connect to whenever they’re in the field,” added Rendon.
DAISI should be ready for transition to commercial availability in the next couple of years. An important next step for developers is the final evaluation of the noise cancelling hardware. This includes safe and effective microphone placement and the successful integration with firefighters’ self-contained breathing apparatus without compromising the integrity of the facepiece seal.
Finally, the development team will provide recommendations for adaption to other first responder communities. Though it has been applied to firefighter use cases thus far, there is great potential for paramedics, police, and members of the military to benefit from this capability as well. In an ever-expanding Internet of Things world, ASR represents the future of emergency response that could enable countless future technologies such as wireless biometric sensors.
“This is a cornerstone technology,” said Ruth Vogel of APL. “If you don’t have the voice recognition capability, then a lot of the other next generation solutions are not going to work well.”