i would have done it's two hundred and i'm going to prison what only spoken
detection
on the spoofing challenge corpus
employing deep neural network
this is actually an extension of our previous work for spoken challenge task
a where you're given actually and
a different spoofing attacks generated using different voice conversion is and speech synthesis technique
and
five i'm on the dandy spoofing attacks one on a prior it was in actually
in the u but evaluation set we had five hundred hz and five one text
so
in this work in this is what would be in this work to overview of
this one
who what right here actually tried to train a the nn
which we will try to discriminate between school and
human this basic and then we try to extract
order thing feature representation and the users would with the standard
a gmm classifier also we use a
tandem feature which is basically concatenation of
bottleneck feature and
acoustic level spoofing detection features and we try to reduce the damage using pca
and then he to use this the gmm classifier
so if you want to know more able or walk and the results based on
that the poster session was a number six thank you