
Sixth International Conference on Spoken Language Processing
(ICSLP 2000)
Beijing, China
October 1620, 2000 

Adjacent Node ContinuousState HMM’s
Carl Quillen
BBN Systems and Technologies, Cambridge, MA, USA
This paper explores properties of a family of Continuous state
hidden Markov models (CSHMM’s) that are proposed for use in
acoustic modeling. These models can be viewed as applying a
smoothing to ordinary HMM’s in order to make estimates of transition
and observation probabilities more robust by sharing data
between adjacent state nodes. They may be trained by EM so
that all parameters properly reflect the applied smoothing. The
amount of smoothing may be trained as well, and the model reverts
to the ordinary HMM in the limit as the smoothing parameters
reach zero. Thus this technique may be employed selectively
only in areas in the model where training data is sparse. This paper
formulates EMtraining for one variant of these models, and
explores their performance when applied to constructing ergodic
CSHMM models of speech and to a phoneme recognition task
on the same data. The ergodic CSHMM did not improve performance
over the HMM, but the phoneme CSHMM’s model the
data with higher likelihood than the equivalent HMM’s, and have
superior recognition accuracy.
Full Paper
Bibliographic reference.
Quillen, Carl (2000):
"Adjacent node continuousstate HMM’s",
In ICSLP2000, vol.1, 425428.