Training the acoustic model

Speech Recognition Toolkit

Brought to you by: air, arthchan2003, awb, bhiksha, and 5 others

This project can now be found here.

Training the acoustic model

Forum: Help

Creator: Vipin Varghese

Created: 2016-09-12

Updated: 2016-09-13

Vipin Varghese - 2016-09-12

Is it necessary to train the model again after adding some words to the dictionary, some new words related to healthcare and medicines.?

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2016-09-12
  
  You do not need to update the acoustic model. You need to update the dictionary and the language model.
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Vipin Varghese - 2016-09-12

dictionary updation i could find how to do,(like a file edit), but how to update the language model.?pls help

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2016-09-12
  
  http://cmusphinx.sourceforge.net/wiki/tutoriallmadvanced
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
  - Vipin Varghese - 2016-09-12
    
    Thanks Nickolay.
    Need small clarification from your side on the following :
    - How to update or create a language model ?
    - What is the structure of a language model ?
    I went through the tutorials and steps on the webpage of cmu sphinx, but couldn't make it up, please guide me to undestand the basic building blocks of a language model. ?
    
    If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
    - Soren Ebbesen - 2016-09-13
      
      I found this guide on youtube quite helpful.
      
      If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Log in to post a comment.