Menu

Why volume normalization is important?

dovark
2015-06-24
2015-06-24
  • dovark

    dovark - 2015-06-24

    Hello,

    It is said here https://sourceforge.net/p/kaldi/discussion/1355348/thread/052a15fd/
    that

    "Normalizing the amplitude of the input is important- at least to have it in
    the right range"

    But since we use CMVN, why would any other kind of normalization will be required at all? Isn't the energy coefficient normalized to fix this issue?

     
    • Daniel Povey

      Daniel Povey - 2015-06-24

      That thread was about the online-nnet2 setup, and it does not use CMVN
      (because that is tricky to implement online), but instead relies on
      the iVectors to represent the cepstral offset and the nnet training to
      use the iVector appropriately. However, if the training data was too
      carefully normalized, or normalized only within a narrow range, it can
      fail to learn complete invariance with respect to volume differences.
      In some more recent recipes we have started perturbing the volume of
      the training data to help it learn this better.
      Dan

      On Wed, Jun 24, 2015 at 7:27 AM, dovark dovark@users.sf.net wrote:

      Hello,

      It is said here
      https://sourceforge.net/p/kaldi/discussion/1355348/thread/052a15fd/
      that

      "Normalizing the amplitude of the input is important- at least to have it in
      the right range"

      But since we use CMVN, why would any other kind of normalization will be
      required at all? Isn't the energy coefficient normalized to fix this issue?


      Why volume normalization is important?


      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/kaldi/discussion/1355347/

      To unsubscribe from further messages, please visit
      https://sourceforge.net/auth/subscriptions/