Multinet is a connectionist architecture designed for certain difficult multi-class pattern classification tasks. These are characterised by very large input feature spaces, rendering a monolithic classifier impractical. The architecture consists of a layer with at least one primary 'detector' for each class, followed by a combining net which estimates the posterior probabilities for all classes. Typically primary detectors only input a subset of the input features. Thus the architecture decomposes classification in two ways: by class and by factoring of the input space dimensions. Multinet incorporates the ideas of Modular Neural Networks and Ensembles. In this paper, we investigate the use of Multinet on standard HMM and hybrid HMM-NN systems that we run on the same tasks. The value and potential of the Multinet approach is shown by detailing successive improvements to the Multinet system which are easily obtained because of the modularity of the architecture.
Cite as: Pizzolato, E.B., Reynolds, T.J. (1998) Initial speech recognition results using the multinet architecture. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0821, doi: 10.21437/ICSLP.1998-405
@inproceedings{pizzolato98_icslp,
author={Ednaldo B. Pizzolato and T. Jeff Reynolds},
title={{Initial speech recognition results using the multinet architecture}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0821},
doi={10.21437/ICSLP.1998-405}
}