infinear.com uses an open source stack which includes Asterisk (PSTN interface), the java Sphinx-4 speech decoder, and a mySQL database for user content on Amazon's EC2.  From their site:

Internally, infinear.com uses the CMU Sphinx-4 decoder. A very fast trainer focused only on phonemes generates acoustic models. A typical training session generates models in a couple of hours on a dual core 2.6GHz box. The CMU-Cambridge Langauge Toolkit generates Langauge Models. The exact dictionary varies for every user and use case. We switch grammars at decode time depending on the user and use case. A typical grammar generation scenario is driven by user content stored in a database. These user specific words are put in a dictionary. A rules-engine generates phoneme sequences for each word. The CMU LM Toolkit generates an LM and a vocab.

--- (Edited on 1/16/2010 3:00 pm [GMT-0500] by kmaclean) ---