Any recommendation on Hypothesis scoring limits?

Home Forums OpenEars Any recommendation on Hypothesis scoring limits?

Viewing 2 posts - 1 through 2 (of 2 total)

  • Author
    Posts
  • #1015440
    Geri
    Participant

    Is there any recommendation on hypothesis scoring limits?
    I’d need around 4 categories, I’m just prototypeing now.

    You said “WORD”.
    Seems you said “WORD”.
    Probably you said something like “WORD”.
    Sorry, I couldn’t understand what you said.

    What could be the hypothesis scrore limits for these?

    #1015441
    Halle Winkler
    Politepix

    Hello,

    Here are the previous discussions:

    https://www.politepix.com/forums/topic/how-does-recognition-score-works/
    https://www.politepix.com/forums/topic/scores-used-in-openears/

    You can’t use ranges to limit because you don’t know what the environmental factors are, but something you can experiment with is detecting cases where the top n-best and the second-closest n-best are close and the overall range is large. i.e. 1-best is -50000 and 2-best is -50500 suggests to me that it’s a close call. But you can’t say “below -50000 is wrong”.

Viewing 2 posts - 1 through 2 (of 2 total)
  • You must be logged in to reply to this topic.