Connectionist Optimisation of Tied Mixture Hidden Markov Models
Abstract
Issues relating to the estimation of hidden Markov model (HMM) local probabilities are discussed. In particular we note the isomorphism of ra(cid:173) dial basis functions (RBF) networks to tied mixture density modellingj additionally we highlight the differences between these methods arising from the different training criteria employed. We present a method in which connectionist training can be modified to resolve these differences and discuss some preliminary experiments. Finally, we discuss some out(cid:173) standing problems with discriminative training.
Cite
Text
Renals et al. "Connectionist Optimisation of Tied Mixture Hidden Markov Models." Neural Information Processing Systems, 1991.Markdown
[Renals et al. "Connectionist Optimisation of Tied Mixture Hidden Markov Models." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/renals1991neurips-connectionist/)BibTeX
@inproceedings{renals1991neurips-connectionist,
title = {{Connectionist Optimisation of Tied Mixture Hidden Markov Models}},
author = {Renals, Steve and Morgan, Nelson and Bourlard, Hervé and Franco, Horacio and Cohen, Michael},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {167-174},
url = {https://mlanthology.org/neurips/1991/renals1991neurips-connectionist/}
}