i apologise we don't have a slight proposed ten but the posters on identification approach
regional accents using fusion of i-vector and multi-accented phonotactic systems and the older the marion
the jfa on sites a five e
phil whether a myself often russell
we have a diversity of regional accents in the british isles and the papers about
trying to recognize fourteen of them
the that the of the work uses two different approaches one based on i-vectors and
the other based on the fusion of a set of fourteen different phonotactic systems so
the first is concerned with
acoustic differences between the different regional accents and the second between the is concerned with
differences in the sequences of phones that are produced in addition accents
unsurprisingly the best performance is obtained by using the two methods together
we have recognition results but also we have an attempt to visualise the i-vector space
where the actions wreck represented it is interesting to look at relationships between the topology
of that space and geographical and social relationships between the actual accents themselves thank you
again i apologise for not having a slot