>This paragraph suggests that the spelling transformation would >proceed the ALPHED transformation.
Probably would have to be a fork rather than pipe, once it was phonemed, I would think it would be hard to get back into recognizable English. Then again that's what IBM ViaVoice and Dragon Dictate do, are there Open source voice recognition projects with an API call into we could inject the phoneme stream? </sarcasm> That should not make too big a dent in CPU utilization </sarcasm> Running an eval on the ALPHED stream and generating a found/unfound ration against a dictionary Keeping a hash of the found words in sequence might help too, although there seems to be a trend in quoting from Project Gutenberg, and random blogs to poison hashing functions, maybe just hash word tuples? Probably to close to current Bayesian methods. Best Regards, Bob ------------------------------------------------------- This SF.net email is sponsored by: IBM Linux Tutorials. Become an expert in LINUX or just sharpen your skills. Sign up for IBM's Free Linux Tutorials. Learn everything from the bash shell to sys admin. Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
