This site may earn chapter commissions from the links on this folio. Terms of use.

Sound Wave iStock

When I was in the second grade, a "frenemy" dared me to punch 911 from a payphone while on a school outing. Minutes subsequently, a police officer arrived at the public park, disbanded all of usa from play, and treated the class to a lecture on the importance of only using 911 during an emergency circumstance. The lesson was not lost upon me, and years later I can however remember the panic I felt, equally the constabulary officer's gaze swept over us like an angry god displeased with his pagan followers.

Unfortunately, thousands of adults routinely place prank calls to the coast baby-sit, police and other emergency service personnel, costing the public both in tax payer dollars and, non infrequently, man lives. It was for this reason the US coast baby-sit reached out to researchers at Carnegie Mellon University to assistance identify a prank caller who had been routinely calling in SOS emergencies to which they were obligated to reply, often putting their own first responders in grave danger.

MIAMI - Two Coast Guard HH-65C Dolphin helicopters from Air Station Miami fly in formation over the Atlantic Ocean. The HH-65 is known for its Fenestron tail rotor and its autopilot capabilities, which can complete an unaided approach to the water and bring the aircraft into a stable 50 foot hover, or automatically fly search patterns, an ability which allows the crew to engage in other tasks. Coast Guard photo by PAC Dana Warr.

Ii Coast Guard HH-65C Dolphin helicopters engaged in a search-and-rescue training operation.

Using cutting-edge machine learning algorithms and signal process technologies, Dr. Rita Singh and her colleagues pieced together a profile of the prank caller solely from recordings of his voice — including a prediction of his elevation, weight, and the size of room he was calling from. When the coast guard finally succeeded in trailing downwards the perpetrator, his profile matched up nigh perfectly with the one generated past the CMU researchers. This generated a flood of interest in Dr. Singh'south work on estimator voice recognition.

As Rita Singh explained to me during a recent chat, even when individuals desire to conceal their vocalization, say past imitating an accent or irresolute modulation, information technology will probable neglect to fool her algorithms. Our voices identify united states most besides every bit our fingerprints. At that place are micro expressions contained inside a voice that happen at a subconscious level and are beyond a person'south control. For instance, the speed at which a person rises from a "t" to an "a" when pronouncing the word "tap" comprises a micro expression that cannot be easily faked or altered.

These advances get well across identifying a person by their voice, though. Through the creative use of signal processing and car learning, Rita'south squad can identify a person's utilize of intoxicants or other substances — and even more surprisingly, the onset of medical conditions the speaker may non even be aware they possess. For instance, the biomarker for Parkinson's tin can be detected in a person'due south vocalisation long before whatever other symptoms arise. This raises the prospect of using voice recognition in the medical field to diagnose diseases with speech-related biomarkers.

Top image credit: