Deep-learning algorithm can mimic any voice based on just 60 seconds of speech

An AI startup called Lyrebird just invented an algorithm that can mimic the voice of any person, based on just 60 seconds of speech. Do you remember the cool Mission Impossible tech that lets Tom Cruise's character Ethan Hunt mimic the voice of other characters using some nifty speech synthesis technology? Well, a Montreal-based startup called Lyrebird (named after the sound-imitating bird) just invented it for real. "We are developing new speech synthesis technologies which, among other features, allow us to copy the voice of someone with very little data," Alexandre de Brebisson, one of the PhD students who developed the deep-learning tech behind the project. "Our experiments show that one minute of audio already contains a lot of the DNA of a human voice. We are able to learn a new voice with as little data because our model is able to capture similarities between the new voice and all the voices it already knows. Our models understand the underlying variables that make [one] voice different from another."