Study shows how often people can identify AI-generated voices

The study was performed by Kimberly Mai at University College London and her colleagues, who used a text-to-speech algorithm trained on two publicly available datasets. Fifty deepfaked speech samples were created in both languages to determine if humans could identify the fakes from the real voices.

Read Entire Article

algorithm article colleagues college datasets fakes generated humans identify languages london people shows speech study text text-to-speech university university college london voices