Dirichlet Process background?

I was reading this introduction to Dirichlet processes http://www.gatsby.ucl.ac.uk/~ywteh/research/npbayes/dp.pdf but I found that I'm not familiar with a lot of concepts and terminology. I have intermediate knowledge of stats, not much beyond regressions and good understanding of common machine learning algorithms (classification, clustering). What background gaps do I need to fill to understand this article? Do I need a first course in Bayesian nonparametrics? Anything even before that? Recommendations are appreciated. Thanks.