Sixth International Conference on Spoken Language Processing
October 16-20, 2000
A Neural Network for Classification with Incomplete Data: Application to Robust ASR
Andrew C. Morris (1), Ljubomir Josifovski (3), Hervé Bourlard (1,2),
Martin Cooke (3), Phil Green (3)
(1) Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP), Martigny, Switzerland
There are many situations in data classification where the data
vector to be classified is partially corrupted, or otherwise
incomplete. In this case the optimal estimate for each class
probability output, for any given set of missing data
components, can be obtained by calculating its expected value.
However, this means that classifiers whose expected outputs do
not have a closed form expression in terms of the original
function parameters, such as the commonly used multi-layer
perceptron (MLP), cannot be used for classification with
missing data. No classifier can compete with the performance of
an MLP on complete data unless it is discriminatively trained.
In this paper we present a particular form of RBF classifier
which can be discriminatively trained and whose expected
outputs are a simple function of the original classifier
parameters, even though the output unit function is non-linear.
This provides us with an incomplete data classifier network
(IDCN) which combines the discriminative classification
performance normally associated with artificial neural
networks, with the ability to deal gracefully with missing data.
We describe two ways in which this IDCN can be applied to
robust automatic speech recognition (ASR), depending on
whether or not the position of missing data is known. We
compare the performance of one of these models with an
existing system for ASR with missing data.
(2) Swiss Federal Institute of Technology (EPFL), Lausanne, Switzetrland
(3) Sheffield University, Dept. of Computer Science, UK
Morris, Andrew C. / Josifovski, Ljubomir / Bourlard, Hervé / Cooke, Martin / Green, Phil (2000):
"A neural network for classification with incomplete data: application to robust ASR",
In ICSLP-2000, vol.1, 409-412.