from the NetBSD maintainer:

	This voice provides an American English male voice using a
	residual excited LPC diphone synthesis module, both created
	at OGI.  It uses a lexicon compiled from MOBY and CMU
	lexicons, and other trained modules used by CSTR voices.
 
This voice can be activated via (voice_aec_diphone) .

WWW:  http://cslu.cse.ogi.edu/tts