> Thanks for the additional instructions. My problem was related to having
the
> sampling rate set to "music" rather than "voice 4K" although I would
expect
> it to recognize with higher accuracy while set to a higher sampling rate.
If the recognition is based on audio pattern recognition an exact sampling
rate as has been used to teach the recognizer would be mandatory. The pkg
should adjust the sampling rate by itself and restore the setting upon
closing. But they've probably left this programming task for later versions
or the MP3000 ;-)
-- With best regards / Viele GruesseMarco Mailand http://slsbd.psi.ch/timing
-- This is the Newtontalk mailinglist - http://www.newtontalk.net To unsubscribe or manage: visit the above link or mailto:newtontalk-request_at_newtontalk.net?Subject=unsubscribe
This archive was generated by hypermail 2.1.2 : Thu Nov 01 2001 - 10:01:50 EST