Re:Real-time emotional voices with D.A.V.I.D
by JoshTriplett on Monday March 28, 2016 @07:37PM
(#11378383)
The concept seems quite interesting. I can hear slight differences between the different versions, but I honestly can't hear those differences as conveying any particular emotion. If you mixed them up and asked me which one sounded most "happy" or most "scared" or most "sad", I'd be stumped.
[ Parent
| on HN ]
Re:Real-time emotional voices with D.A.V.I.D
by fluxist on Monday March 28, 2016 @10:59PM
(#11379191)
Nor can I very well. After some googling, I see that apparently this would be called "auditory affective agnosia" (if it were at the level of neuropsychological pathology). I wonder if this software could be used diagnostically in disorders that are associated with deficits in empathy or emotional identification -- autism, Antisocial or Narcissistic Personality Disorders, etc.
Perhaps it could also be used as a therapeutic tool. One could train with it in order to reduce the affective threshold at which one detects emotion.
Re:Real-time emotional voices with D.A.V.I.D
by JoshTriplett on Tuesday March 29, 2016 @10:40AM
(#11381764)
> One could train with it in order to reduce the affective threshold at which one detects emotion.
Interesting idea. If software like this can smoothly adjust intensity, you could find the threshold at which you can reliably detect it, and attempt to push that downward to pick up more subtlety.