There are couple of messages on open source speech recognition on iOS. That certainly caught my eyes. For now, I believe one of most well-known names is OpenEars. It is built up on PocketSphinx and it provides speech synthesis functionalities as well.
It looks pretty promising. So I will probably start to play with it as well.
I just added a link of OpenEars here in the Grand Janitor's Blog. Btw, I should think of better syndicate different ASR-related site.