0:00:15i would have done it's two hundred and i'm going to prison what only spoken
0:00:23on the spoofing challenge corpus
0:00:26employing deep neural network
0:00:28this is actually an extension of our previous work for spoken challenge task
0:00:34a where you're given actually and
0:00:37a different spoofing attacks generated using different voice conversion is and speech synthesis technique
0:00:48five i'm on the dandy spoofing attacks one on a prior it was in actually
0:00:55in the u but evaluation set we had five hundred hz and five one text
0:01:01in this work in this is what would be in this work to overview of
0:01:06this one
0:01:07who what right here actually tried to train a the nn
0:01:12which we will try to discriminate between school and
0:01:16human this basic and then we try to extract
0:01:20order thing feature representation and the users would with the standard
0:01:23a gmm classifier also we use a
0:01:27tandem feature which is basically concatenation of
0:01:31bottleneck feature and
0:01:34acoustic level spoofing detection features and we try to reduce the damage using pca
0:01:40and then he to use this the gmm classifier
0:01:44so if you want to know more able or walk and the results based on
0:01:48that the poster session was a number six thank you