Changes between Version 2 and Version 3 of AcousticTreeQuestions


Ignore:
Timestamp:
09/26/07 11:25:33 (12 years ago)
Author:
kmaclean
Comment:

minor edits & added link to HTK question file

Legend:

Unmodified
Added
Removed
Modified
  • AcousticTreeQuestions

    v2 v3  
    1 Since continuous speech is very context-dependent and variable it's not sufficient to build model for each phone, acoustics can differ sufficiently if phone is used in different context. That's why for continuous speech often context-dependent models are used. Models doesn't depend on phone name but on the name of next and previous phones and probably on many more parameters. Of course it's not possible to build a model for all combinations of arguments, moreover their number can exceed hundred. That's why usually training software either select the set of models automatically or with a little input from the user. 
     1Since continuous speech is very context-dependent and variable it's not sufficient to build model for each phone, acoustics can differ sufficiently if phone is used in different context. That's why for continuous speech context-dependent models are often used. Models don't depend on phone name but on the name of next and previous phones and probably on many more parameters. Of course it's not possible to build a model for all combinations of arguments, moreover their number can exceed hundred. That's why training software usually either selects the set of models automatically or with a little input from the user. 
    22 
    33For example sphinx can build set of models automatically. HTK requires you to pass the list of properties model selection will use and will do the rest itself. Of course if you have hand-made questions it's better to submit them to sphinx too, moreover it allows it.  
     
    2323 * Any other group of phones 
    2424 
    25 I hope you get the idea, now repeat questions for each context - question for left context, right context and phone itself. The result should look like http://www.dev.voxforge.org/projects/Russian/browser/Trunk/AcousticModels/etc/msu_ru_nsh.tree_questions 
     25I hope you get the idea, now repeat questions for each context - question for left context, right context and phone itself. The result should look like [http://www.dev.voxforge.org/projects/Russian/browser/Trunk/AcousticModels/etc/msu_ru_nsh.tree_questions this for Sphinx]  or like [http://www.dev.voxforge.org/projects/Main/browser/Trunk/Scripts/AcousticModel_scripts/HTK/AMCreate_scripts/input_files/tree1.hed this for HTK] 
    2626 
    2727The number of questions should be small since otherwise you have to collect too much data to train all models. It's recommended to have 20-30 questions for the tree.