News for hackers. Stuff that matters.

A comment on Ask HN: Who is looking for a co-founder?. Parent comment

Re:Ask HN: Who is looking for a co-founder? by Caligula on Thursday August 20, 2009 @04:34PM (#776134)
Not like either except for the speech component. Yours can be done using the speech open src sft but the accuracy will be bad unless you buy or make a good acoustic model. Very painful.
[ Parent | on HN ]
Re:Ask HN: Who is looking for a co-founder? by jcrocholl on Thursday August 20, 2009 @04:47PM (#776180)
Yes, but the acoustic model (or models if you account for male/female and different accents) can be improved with all the input that the service gets over time. The bad accuracy can be fixed by human intelligence using Amazon Mechanical Turk.
[ Parent | on HN ]