Mar 6, 2018

Baidu’s creepy new AI can accurately mimic your voice

Posted by in category: robotics/AI

Researchers from the Beijing-based technology firm trained its text-to-speech synthesis system on more than 800 hours of audio, taken from around 2,400 different speakers.

To work at its best, Deep Voice requires 100 five-second sections of sound but it can trick a voice recognition system 95 per cent of the time with just ten five-second samples.

The technology could duplicate the voices of people who have lost the ability to use their voice, developers say.

Read more

Comments are closed.