FBI Developing VoiceGrid Nation Based on Russian Biometric Speech Recognition Technology
Russia’s Speech Technology Center, which operates under the name SpeechPro in the United States, has invented what it calls “VoiceGrid Nation,” a system that uses advanced algorithms to match identities to voices. The idea is that it enables authorities to build up a huge database containing up to several million voices—of known criminals, persons of interest, or people on a watch list. Then, when authorities intercept a call and they’re not sure who is speaking, the recording is entered into the VoiceGrid and it comes up with a match. It takes just five seconds to scan through 10,000 voices, and so long as the recording is decent quality and more than 15 seconds in length, the accuracy, SpeechPro claims, is at least 90 percent.
When I ask Khitrov about this, he uses an analogy about the character Raskolnikov from Dostoyevsky’s Crime and Punishment, who killed an old woman with a stolen ax. “People have used axes domestically for hundreds of years, but some people choose to turn it into a weapon,” he says. “We just make sure that we work with trusted law enforcement agencies and try to make sure that they use it properly.” SpeechPro’s technology is used for only “very noble causes,” he adds, citing a case in Mexico where he says it was used to identify and find kidnappers who made ransom calls before they were about execute a person. Though when I ask for more examples of how VoiceGrid is being used in Mexico, he admits, “We don’t know the specifics because that’s their information.”