Speech is becoming more human & less robotic for “Robotic Human Speech”.
Google’s DeepMind AI is learning how to talk and how to do it like a person, not a robot. Right now DeepMind AI has many learning projects going on, but the newest one to catch our ears seems to be an increasingly realistic voice and speech pattern system that eliminates more and more of the inhuman, robotic patterns we use to identify computers.
MIT released results from a new AI program today that turns images into video by knowing how a video of that image is supposed to move (though the videos are kind of frightening if you look too close). Machines are getting better at a lot of things.
Imagine if Siri, Cortana, or Alexa started having inflection, variances, and realistic breathing patterns. Instead of sounding like this, it might sound like this. By playing existing recordings for the AI system, the researchers will help the system to overtime incorporate those patterns and inflections into its speech.
So very soon, when you hear a voice on a phone, it may be harder to tell if you’re hanging a person or computer. But let’s just hope Google’s AI doesn’t start hearing voices telling it to do things.