| |
Abstract:
(MALCOM), an alternative to hidden Markov models (HMMs) for
processing sequence data such as speech. While HMMs have a discrete
``hidden'' space constrained by a fixed finite-automaton
architecture, MALCOM has a continuous hidden space---a continuity
map---that is constrained only by a smoothness requirement on paths
through the space. MALCOM fits into the same probabilistic
framework for speech recognition as HMMs, but it represents a more
realistic model of the speech production process. To evaluate the
extent to which MALCOM captures speech production information, we
generated continuous speech continuity maps for three speakers and
used the paths through them to predict measured speech articulator
data. The median correlation between the MALCOM paths obtained from
only the speech acoustics and articulator measurements was 0.77 on
an independent test set not used to train MALCOM or the predictor.
This unsupervised model achieved correlations over speakers and
articulators only 0.02 to 0.15 lower than those obtained using an
analogous supervised method which used articulatory measurements as
well as acoustics.
|
