Menu

state tying

Help
asr2010
2012-03-02
2012-09-22
  • asr2010

    asr2010 - 2012-03-02

    I can always find new triphones in the final .mdef file that have never been
    seen in the training data (untied.mdef). the number of triphones is always
    higher in the final mdef file. I need to restrict the triphone models to be
    only for those which have been seen in the training data. for the unforseen
    triphones, the decoder should backoff to the CI models. my questions: why the
    trainer propose new triphones? is it possible to avoid that?

     
  • Nickolay V. Shmyrev

    my questions: why the trainer propose new triphones?

    It collects all possible triphones from your dictionary. If you configure it
    to use too many triphones it will pick some additional ones.

    is it possible to avoid that?

    Use less tied states in training configuration

     
  • asr2010

    asr2010 - 2012-03-02

    It collects all possible triphones from your dictionary. If you configure it
    to use too many triphones it will pick some additional ones.

    The added triphones to the final mdef file do not exist in any single word in
    the dictionary as well. Does the trainer consider the combination of any two
    words in the dictionary?

    Use less tied states in training configuration

    less tied states doesn't have any effect on the number of triphones. it
    affects only the number of shared states!

     
  • Nickolay V. Shmyrev

    Does the trainer consider the combination of any two words in the
    dictionary?

    Yes, it should consider cross-word triphones. You can see it in position
    field. However, I think it does the right think by assigning tied states with
    decision tree, not falling back to CI. It seems more reasonable.

    less tied states doesn't have any effect on the number of triphones. it
    affects only the number of shared states!

    Right, i was confused initially. I'd like to note that trainer doesnt "train
    new triphones". It trains only tied states parameters which has been seen in
    the data.

     

Log in to post a comment.