Abstract
In this paper the MLP and Gaussian mixture model approaches to the estimation of the posterior probability of class membership in the task of phoneme identification are analyzed. The paper discuss differences between the described methods altogether with discussing advantages and drawbacks of each method. Based on this analysis several ways of the joint employment of the models are proposed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
C. Bishop “Neural Networks For Pattern Recognition” Clarendon Press, Oxford 1995, pp. 482.
H. Bourlard, N. Morgan “Connectionist Speech Recognition, A Hybrid Approach” Kluwer Academic Publishers, Boston, Dordrecht, London 1994, pp. 312.
B. Ripley “Pattern Recognition and Neural Networks” Cambridge University Press, 1996.
R. M. Golden “Mathematical Methods for Neural Network Analysis and Design” The MIT Press, 1996.
Y. Bengio “Neural Networks for Speech and Sequence Recognition” International Thomson Computer Press, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ivanov, A.V., Petrovsky, A.A. (1999). MLPs and Mixture Models for the Estimation of the Posterior Probabilities of Class Membership. In: Matousek, V., Mautner, P., Ocelíková, J., Sojka, P. (eds) Text, Speech and Dialogue. TSD 1999. Lecture Notes in Computer Science(), vol 1692. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48239-3_39
Download citation
DOI: https://doi.org/10.1007/3-540-48239-3_39
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66494-9
Online ISBN: 978-3-540-48239-0
eBook Packages: Springer Book Archive