Home › Forums › OpenEars › Hypothesis recognition scores › Reply To: Hypothesis recognition scores
April 11, 2013 at 7:48 am
#1016924
Halle Winkler
Politepix
Correct, they are probabilities with zero being certainty. They don’t have an enormous amount of utility (they are very subject to environmental conditions so you can’t use any kind of objective cutoff from session to session in order to say that a probability is too low) but you can compare them to each other within a single session, for instance.