Links between Markov models and multilayer perceptrons
Bourlard, H.
Wellekens, C.J.
Philips Res. Lab., Louvain-la-Neuve;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Dec 1990
Volume: 12,
Issue: 12
On page(s): 1167-1178
ISSN: 0162-8828
References Cited: 46
CODEN: ITPIDJ
INSPEC Accession Number: 3858025
Digital Object Identifier: 10.1109/34.62605
Current Version Published: 2002-08-06
Abstract
The statistical use of a particular classic form of a
connectionist system, the multilayer perceptron (MLP), is described in
the context of the recognition of continuous speech. A discriminant
hidden Markov model (HMM) is defined, and it is shown how a particular
MLP with contextual and extra feedback input units can be considered as
a general form of such a Markov model. A link between these discriminant
HMMs, trained along the Viterbi algorithm, and any other approach based
on least mean square minimization of an error function (LMSE) is
established. It is shown theoretically and experimentally that the
outputs of the MLP (when trained along the LMSE or the entropy
criterion) approximate the probability distribution over output classes
conditioned on the input, i.e. the maximum a posteriori probabilities.
Results of a series of speech recognition experiments are reported. The
possibility of embedding MLP into HMM is described. Relations with other
recurrent networks are also explained
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
