Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Class-Based Variable Memory Length Markov Model

Shinsuke Mori, Gakuto Kurata

IBM Japan Ltd., Japan

In this paper, we present a class-based variable memory length Markov model and its learning algorithm. This is an extension of a variable memory length Markov model. Our model is based on a class-based probabilistic suffix tree, whose nodes have an automatically acquired word-class relation. We experimentally compared our new model with a word-based bi-gram model, a word-based tri-gram model, a class-based bi-gram model, and a word-based variable memory length Markov model. The results show that a class-based variable memory length Markov model outperforms the other models in perplexity and model size.

Full Paper

Bibliographic reference.  Mori, Shinsuke / Kurata, Gakuto (2005): "Class-based variable memory length Markov model", In INTERSPEECH-2005, 13-16.