a good afternoon
so in this at one
allpass in this a new method call between class covariance collection to improve language recognition
performance
the we conducted our experiments on the nist lre two thousand fifteen corpus though see
that the corpus is organized like there are twenty languages and each of them are
grouped into six clusters based on their phonetic similarities like you have a rabbit cluster
which has all the grabbing dialects of english and french all these clusters so we
followed a very interesting thing when we
a lot all the i-vectors when the past into the pca and these are the
first two dimensions of the first two base of pca so we found that
the all these languages are grouped together in the form of clusters and all of
these clusters
so you can see that all the languages going to the chinese cluster they are
grouped together
a belong to be i've been a cluster there are grouped together
so they are wonderful multimodal distribution
and so we so we computed the eigen directions representing this multimodal distribution and we
added them to the lda
initial some improvement in performance
so you wanna
no more you in the post animal is once i welcome you all their and
to get the more details about it things