September 22-25, 1997
Phonetic decision trees have been widely used for obtaining robust context-dependent models in HMM-based systems. There are five key issues to consider when constructing phonetic decision trees: the alignment of data with the chosen phone classes; the quality of the modelling of the underlying data; the choice of partitioning method at each node; the goodness-of-split criterion and the method for determining appropriate tree sizes. A popular existing method usesefficient but crude approximatemethods for each of these. This paper introduces and evaluates more detailed alternatives to the standard approximations.
Bibliographic reference. Nock, H. J. / Gales, M. J. F. / Young, Steve J. (1997): "A comparative study of methods for phonetic decision-tree state clustering", In EUROSPEECH-1997, 111-114.