Realistic voice generation technology has gotten uncannily good in the past few years. In some situations, it’s possible to generate a synthetic voice that sounds almost exactly like the voice of a real person. And today, what once felt like science fiction is reality: Voice cloning. With just a few seconds of recorded speech, anyone’s voice can be made to say almost anything.

Voice generation, and in particular the subtask of voice cloning, has notable risks and benefits. The risks of “deepfakes”, such as the cloned voice of former President Biden used in robocalls, can mislead people into thinking that people have said things that they haven’t said. On the other hand, voice cloning can be a powerful beneficial tool, helping people who’ve lost the ability to speak communicate in their own voice again, or assisting people in learning new languages and dialects.

So how do we create meaningful use without malicious use? We’re exploring one possible answer: a voice consent gate. That’s a system where a voice can be cloned only when the speaker explicitly says they consent. In other words, the model won’t speak in your voice unless you say it’s okay.

The voice consent gate is a piece of infrastructure we're exploring that provides methods for ethical principles like consent to be embedded directly into AI system workflows. In our demo, this means the model only starts once the speaker’s consent phrase has been both spoken and recognized, effectively making consent a prerequisite for action.

Source link