hello everyone so
this looks we but in this presentation i'm just presenting how to use i-vectors for
speech activity detection
so actually this is the what was done in the context of the nist open-set
channels that use actually very tough later that probably many of your nose
and all right speaker on rats data
so the proposed technique is actually to make i-vectors work in the scenario so what
i did is that i first cluster the data in it to unsupervised manner one
of them is based on what they should clustering mainly a k-means plus gmm clustering
and the other one is actually based on
more accurately clustering after some kind of segmentation
and the so then the output of this clusters idea is i can classify them
using different kind of a classifiers i tried the i-vector extract i-vectors of agenda and
and the results are quite the promising
probably bit complex system but the output of this l this class that can be
used not only for speech detection but also for other tasks like their decision about
or what you event detection or and so please the zero by posted to your
interest like