This is the homepage of Dan Povey, speech recognition researcher.  As of Feb 2012, I am a research scientist at the Center for Language and Speech Processing, at Johns Hopkins University.  Contact me at dpovey@gm**l.com or dpovey1@jhu.e*u.

(Search terms including places I have lived or studied or worked: Bethesda; Bangor; York, U.K.; Great Ayton; Grenada; Peterhouse, Cambridge; Greenwich, CT; Yorktown Heights)

For more information on the Kaldi speech recognition toolkit, it has its own webpage on Sourceforge, here.

Slides from the lecture series on Kaldi, currently being delivered, are here

This page describes the things I'm currently thinking about relating to speech recognition.

[some family members' websites:]