Is the process of taking the text transcription of an audio speech segment and determining where in time particular words occur in the speech segment. 

As opposed to speech recognition, where the object is to take an audio speech segment and generate its text transcription.

For more info, see:

• ISIP Tutorial: 4.4.1 Forced Alignment : Overview
• ICSI Speech FAQ: 7.4 What is forced alignment?

Speech Recognition Engines that can perform forced alignment (from command line or script):

• Sphinx
• Julius
  
• HTK

GUI Programs:

• SPPAS (SPeech Phonetization Alignment and Syllabification) (uses Julius and Praat)
  

Other Information:

• Automated Audio Segmentation Using Forced Alignment
• AutoCap - Automatic and Accurate Captioning (
http://imj.ucsb.edu/autocap/ )