0:00:14a good afternoon
0:00:17so in this at one
0:00:19allpass in this a new method call between class covariance collection to improve language recognition
0:00:25the we conducted our experiments on the nist lre two thousand fifteen corpus though see
0:00:31that the corpus is organized like there are twenty languages and each of them are
0:00:34grouped into six clusters based on their phonetic similarities like you have a rabbit cluster
0:00:38which has all the grabbing dialects of english and french all these clusters so we
0:00:43followed a very interesting thing when we
0:00:46a lot all the i-vectors when the past into the pca and these are the
0:00:51first two dimensions of the first two base of pca so we found that
0:00:55the all these languages are grouped together in the form of clusters and all of
0:00:58these clusters
0:01:00so you can see that all the languages going to the chinese cluster they are
0:01:04grouped together
0:01:05a belong to be i've been a cluster there are grouped together
0:01:07so they are wonderful multimodal distribution
0:01:10and so we so we computed the eigen directions representing this multimodal distribution and we
0:01:15added them to the lda
0:01:18initial some improvement in performance
0:01:20so you wanna
0:01:21no more you in the post animal is once i welcome you all their and
0:01:25to get the more details about it things