Forced Alignment - getting started

Speech Recognition Toolkit

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

This project can now be found here.

Forced Alignment - getting started

Forum: Help

Creator: Andrew Carpenter

Created: 2020-10-22

Updated: 2020-10-22

Andrew Carpenter - 2020-10-22

I've been searching around for a clear example on what to run in order to get a forced alignment output for a bunch of wav files that I have. I'm expecting the output to be something that aligns phonemes with start and end times. Been trying to follow along just setting up a training enviorment, but I've yet to come across something that really explains the setup necessary for forced alignment. This article is the closest thing I could find:
https://cmusphinx.github.io/wiki/pocketsphinx_pronunciation_evaluation/

I have my entire project up on this github repo:
https://github.com/arcman7/cmu_sphinx

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2020-10-22
  
  You can check https://montreal-forced-aligner.readthedocs.io/en/latest/
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
  - Andrew Carpenter - 2020-10-22
    
    The solution here being not to use cmusphinx?
    
    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.