Comment by josho

For those not familiar with the NIST 2000 Switchboard evaluation[1] it is a series of 8kHz audio recordings (ie. crappy phone quality samples) of a conversation, including things like "uhhuh" and other pause words. So, 6% seems pretty good.

[1] http://www.itl.nist.gov/iad/mig/tests/ctr/2000/h5_2000_v1.3....