INTERSPEECH 2004 - ICSLP
In this article we present an alternative method for defining the question set used for the induction of acoustic phonetic decision trees. The method is data driven and employs local similarities between the probability density functions of hidden Markov models. The method is shown to work at least as well as the standard method using question sets devised by human experts.
Bibliographic reference. Diehl, Frank / Moreno, Asuncion (2004): "Acoustic phonetic modeling using local codebook features", In INTERSPEECH-2004, 709-712.