Abstract
We describe the Multinet speech classifier architecture. This consists of a framework for combining specialised phone detection networks into a posterior probability estimator for all phones. We explain how individual nets may be trained on different input data representations and time-scales, and yet how their outputs may be combined in a consistent and meaningful manner. We give results showing the benefits of such a division of the classification problem by looking at the performance of the architecture on plosives.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Renais S, Morgan N, Bourlard H et al. Connectionist probability estimators in HMM speech recognition. IEEE Trans on Speech and Audio Processing 1994; 2:161–173
Robinson AJ, Hochberg M and Renais S. The use of recurrent networks in continuous speech recognition. Advanced Topics in automatic speech recognition, eds Lee C-H and Soong FK. chapter 7, Kluwer Academic, 1996
Anand R, Mehotra K, Mohan CK and Ranka S. Efficient classification for multiclass problems using modular neural networks. IEEE Trans on Neural Networks 1995; 6:117–124
Jordan MI and Jacobs RA. Hierarchical Mixtures of Experts and the EM algorithm. Neural Computation 1994, 6(2): 181–214
Fritsch J. ACID/HNN: A framework for hierarchical connectionist acoustic modelling. Proc IEEE Workshop on Automatic Speech Recognition and Understanding, 1997
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London
About this paper
Cite this paper
Reynolds, T.J., Pizzolato, E.B., Antoniou, C. (1998). Multinet: A New Connectionist Architecture for Speech Recognition. In: Niklasson, L., Bodén, M., Ziemke, T. (eds) ICANN 98. ICANN 1998. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1599-1_36
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1599-1_36
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-76263-8
Online ISBN: 978-1-4471-1599-1
eBook Packages: Springer Book Archive