I've used technologies (Nuance??) that have significantly lower errors rates than this, even for systems I have not trained personally. Is there something I'm missing?
Switchboard (http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=...) is a set of telephone conversations between two people. Speakers tend to say a lot of "ums", abruptly restart an utterance in progress, talk past the telephone handset, etc. Dictated speech, especially when speakers know they're talking to a computer, has less acoustic and linguistic noise.
Also let's not forget that the word-level error rate can be reduced by using statistical data about words sequences.