Click here to register.

How-to: Create Acoustic Model - with Script

This How-to describes the creation of an Acoustic Model for the Julius Speech Recognition Engine using the HTK toolkit.  It follows the approach used by the tutorial in the HTK book, but uses a script to automate most of the steps.

Table of Contents 

Download HTK, Julius & Audacity
Data Preparation
    Step 1 - Task Grammar
    Step 2 - Pronunciation Dictionnary
    Step 3 - Recording the Data
    Step 4 - Create HTK Training Script
Run Acoustic Model Creation Script
Run Julian Live
Upload Speech Audio Files

All the files related to this tutorial (except the HTK scripts) are located in this archive file:

voxforge_tutorial_auto-0.1.tgzvoxforge_tutorial_auto-0.1.tgz

Comments

AddSearch