4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Improving Decision Trees for Acoustic Modeling

Ariane Lazaridès (1), Yves Normandin (2), Roland Kuhn (1)

(1) Centre de recherche informatique de Montréal (CRIM)
(2) Locus Speech Corporation, McGill College, Montréal, Québec, Canada

In the last few years, the power and simplicity of classification trees as acoustic modeling tools have gained them much popularity. In [1], we studied "tree units", which cluster parameters at the HMM level. Building on this earlier work, we examine some new variants of Young et al’s "tree states", which cluster parameters at the state level [2]. We have experimented with: 1. Making unitary models (which contain additional information about the context) 2. Pruning trees with various severity levels (idea introduced in [1]) 3. Pooling some leaves (idea adapted from [2]) 4. Refining the questions 5. Questions about the position of the phone within the word 6. Lookahead search 7. Making a single tree for each phone

Full Paper

Bibliographic reference.  Lazaridès, Ariane / Normandin, Yves / Kuhn, Roland (1996): "Improving decision trees for acoustic modeling", In ICSLP-1996, 1053-1056.