[Corpora-List] funded Ph.D. studentship: speech recognition using dynamic Bayesian networks

[Simon King]

**** Funded Ph.D. studentship available ****

Centre for Speech Technology Research
University of Edinburgh, UK
www.cstr.ed.ac.uk

Dynamic Bayesian networks for speech recognition
------------------------------------------------

Hidden Markov models (HMMs) are the current model of choice for
automatic speech recognition (ASR). Although they are seemingly very
simple models, in fact they require a complex system of
context-dependent models, parameter sharing and adaptation algorithms to
achieve the best performance.

HMMs are a member of a wider family of models - dynamic Bayesian
networks (DBNs). There are an infinite variety of other DBNs waiting to
be tried for ASR. DBNs can be formulated to reflect our understanding of
the speech signal; one example of this would be multi-streamed DBNs
(such as the factorial HMM) in which the factors have explicit
linguistic interpretations - the factors might represent aspects of the
speech production process.

Dependencies can be introduced between these hidden factors, creating
ever richer model structures (at the cost of increased computational
complexity). The goal is to find model structures that improve
recognition accuracy whilst remaining computationally feasible.

We have already started exploring various forms of DBN, but there is
still a lot of scope for exciting and original research in this area.
The toolkits and compute power are now available to work with models
that were intractable until recently. It may be that some of the
techniques developed for HMMs can be transferred to DBNs, or we could
build things like parameter tying, pronunciation variation, language
modeling and adaptation into the model structure itself.

Full funding (fees plus living allowance) for eligible UK or EU students
is available.

Contact Dr. Simon King <Simon.King at ed.ac.uk> for more information or see
http://www.cstr.ed.ac.uk/opportunities/phd.html for application information.

--
Dr. Simon King                               Simon.King at ed.ac.uk
Centre for Speech Technology Research          www.cstr.ed.ac.uk
For MSc/PhD info, visit  www.hcrc.ed.ac.uk/language-at-edinburgh