• trolololol@lemmy.world
    link
    fedilink
    English
    arrow-up
    1
    ·
    7 months ago

    Yep it’s part of it to generate the sound track

    One of the videos show the voice changing in mid sentence

    • kromem@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      edit-2
      7 months ago

      No, it isn’t. In that clip they are taking two different sound clips as they are switching faces. It’s not changing the ‘voice’ of saying some phrase on the fly. It’s two separate pre-recorded clips.

      Literally from the article:

      It does not clone or simulate voices (like other Microsoft research) but relies on an existing audio input that could be specially recorded or spoken for a particular purpose.