0:00:14so high and gregory usually and form in c and i'll be presenting the work
0:00:21we did with a bow capture research in preparation for than nist language recognition evaluation
0:00:27of to some fifteen
0:00:31so what would it is we just to did for different systems and phonotactic one
0:00:36us an i-vector system
0:00:39a long short-term memory recurrent neural network and the lexical couple component
0:00:45and the main results
0:00:47that can sure but i will be happy to discuss more a new of the
0:00:54on that the l s t m r and then can lead to a lower
0:00:57and lower language error rate than i-vectors
0:01:02still the phonotactic system is the most robust with a method especially when you data
0:01:08are available for language
0:01:11and when facing are very strong mismatch between training and testing which was the case
0:01:17for the lre or fifteen
0:01:20and a what's worse really interesting for ice is that the phonotactic system and the
0:01:26l s t n r and then really combined their combine really well in that
0:01:32the combination of the two system lead to an important a language or rate reduction
0:01:38and if you want to know more about the few euros here
0:01:41i you have to come and see the poster in speaker and me thank you