Listen very carefully (Image: Gilles Coulon/Tendance Floue)
NOW your phone knows you better than ever. The latest version of Apple鈥檚 mobile operating system learns what your voice sounds like, and can identify you when you speak to Siri, ignoring other voices that try to butt in.
Advertisement
Siri, the intelligent personal assistant, is not the only one who knows your voice. As learning software improves, voice-identification systems have started to creep into everyday life, from smartphones to police stations to bank call centres. More are probably on the way. In a paper at the end of September, researchers at Google unveiled an artificial neural network that could verify the identity of a speaker saying 鈥淥K Google鈥� with an error rate of 2 per cent.
Voice is a 鈥�physiological phenomenon鈥� shaped by your physical characteristics and the languages you speak, says Roger Moore at the University of Sheffield in the UK. A passphrase such as 鈥淗ey Siri鈥� or 鈥�OK Google鈥� is a powerful way to verify that you are who you say you are, he adds.
鈥淢y voice is different from your voice, which is different from your mother鈥檚 voice, which is different from someone on the far side of the world,鈥� Moore says. 鈥淭he latest machine-learning techniques can tease apart the tiny differences.鈥�
For machines, recognising individual voices is different from understanding what they are saying. The recognition software has been fuelled by massive sets of vocal data built into a huge model of how people speak. This allows measurements of how much a person鈥檚 voice deviates from that of the overall population, which is the key to verifying a person鈥檚 identity. Changes to someone鈥檚 voice due to sickness or stress can throw off the software.
The technology is already being used in criminal investigations. Last year, when journalist James Foley was beheaded, apparently by ISIS, police used it to compare the killer鈥檚 voice with that of a list of possible suspects. And the banks JP Morgan and Wells Fargo have started using voice biometrics to figure out whether people calling their helplines are scam artists.
Your voice doesn鈥檛 just give away who you are, but what you鈥檙e like and what you鈥檙e doing, says Rita Singh at Carnegie Mellon University in Pittsburgh, Pennsylvania. 鈥淵our speech is like your fingerprints or your DNA.鈥�
鈥淵our voice doesn鈥檛 just give away who you are, but what you鈥檙e like and what you鈥檙e doing鈥�
Singh is figuring out how to build profiles of a stranger from audio recordings. A voiceprint gives insight into the speaker鈥檚 height and weight, their demographic background, and even what their environment is like. She is working with doctors in Massachusetts and Ohio to detect a person鈥檚 likely diseases or psychological state through voice analysis.
Having devices in the home that recognise voices does raise security concerns, especially if they understand what you鈥檙e saying. Speech and voice algorithms often aren鈥檛 embedded in the device itself; instead, what you say is sent to a server somewhere else for analysis, and then ported back quickly. For example, Samsung fell into hot water this year with the revelation that its smart TVs could record private conversations.
鈥淭here are privacy concerns everywhere,鈥� says Singh. 鈥淭here is no device out there that ensures privacy.鈥�
This article appeared in print under the headline 鈥淥K computer, who am I?鈥�
