Menu

HMM Basics

Vamsi
2014-07-30
2014-07-31
  • Vamsi

    Vamsi - 2014-07-30

    I have been trying to understand the use of HMM in acoustic modelling. From what I read, I can see that for large vocabulary speech recognition requirements, triphone HMMs are used with senones as states of the HMM.
    Is my understanding correct?
    If yes, here is my further question.
    Given that a HMM can model multiple state transitions between the 3 senones, is it that one HMM be used to represent multiple triphones? I am imagining that multiple state transition possibilities can result in multiple triphones being represented by the same HMM.

     
    • Nickolay V. Shmyrev

      Is my understanding correct?

      Yes

      Given that a HMM can model multiple state transitions between the 3 senones, is it that one HMM be used to represent multiple triphones?

      Yes, it is possible. For example triphones like B-A-S and B-A-Z might be represented by the same senone sequence since their acoustic properties are simialr.

      I am imagining that multiple state transition possibilities can result in multiple triphones being represented by the same HMM.

      Transitions are shared for triphones of the same base phone so if triphone is represented by the same senone sequence, the transitions between states are the same.

       
  • Vamsi

    Vamsi - 2014-07-31

    Hello Nickolay- Thanks for clarifying.

    I have a further question.
    If same senone sequence from a HMM can be used to model multiple triphones,can different senones sequences from a HMM too be used multiple triphones?

    For example if senone sequence S1--> S2--> S3 of a HMM is used to model Triphone1,
    can S1-->S1-->S2 from from the same HMM be used to model Triphone2?

    If yes, can you share an example?

     
    • Nickolay V. Shmyrev

      For example if senone sequence S1--> S2--> S3 of a HMM is used to model Triphone1, can S1-->S1-->S2 from from the same HMM be used to model Triphone2?

      Yes

      If yes, can you share an example?

      You can find many examples in mdef file in any acoustic model

       
    • Bhiksha Raj

      Bhiksha Raj - 2014-07-31

      Sure. Happens all the time.

      The point is, we're actually performing a search over a graph of
      words, and the words are composed of triphones. So having identical
      models for two triphones doesn't really matter that much since the
      word models will be different anyway. Sometimes the word models too
      will be identical (e.g. two words with the same pronunciation), in
      which case we depend on the structure of the word graph (which is
      given by the language model) to disambiguate.

      -Bhiksha

      On Thu, Jul 31, 2014 at 12:28 AM, Vamsi vamsiev@users.sf.net wrote:

      Hello Nickolay- Thanks for clarifying.

      I have a further question.
      If same senone sequence from a HMM can be used to model multiple
      triphones,can different senones sequences from a HMM too be used multiple
      triphones?

      For example if senone sequence S1--> S2--> S3 of a HMM is used to model
      Triphone1,
      can S1-->S1-->S2 from from the same HMM be used to model Triphone2?

      If yes, can you share an example?


      HMM Basics


      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/cmusphinx/discussion/speech-recognition/

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

      --
      Bhiksha Raj
      Carnegie Mellon University
      Pittsburgh, PA, USA
      Tel: 412 268 9826

       
  • Vamsi

    Vamsi - 2014-07-31

    Nicholay/Bishaka- Thank you! That helped.

     

Log in to post a comment.