0:00:15but i and i'm looking at automatic accent recognition in the context of forensic applications
0:00:22so forensic speech scientist have access to use a speaker recognition technology so you assess
0:00:30multiple recordings and to see how likely it is that the speech in these recordings
0:00:36were produced by the same speaker
0:00:38other kinds of cases i one might be interested in the speech community and then
0:00:43nine speaker or hunting speakers belonged c and i'm investigating whether we can apply automatic
0:00:50accent recognition c and this kind of problem
0:00:55so i'm
0:00:56a one step towards doing that and this that i'm taking with the place to
0:01:01do that is and see you investigate whether an automatic accent recognition technology can work
0:01:08on and while i'm having geographically proximate accent
0:01:13and the assumption here is that and that's a greater degree of similarity between these
0:01:19different accents eh i'm evaluating five different automatic accent recognition systems
0:01:26an eight corpus or else
0:01:29for accents
0:01:30and
0:01:31which is from the i subcorpus
0:01:34and i've got before locations and within their use pads with only got ten miles
0:01:40sitting between like
0:01:42stereo we do next
0:01:44to find differences between these accent variety
0:01:47and
0:01:48but we expect us differences and well just high degree of similarity study i'm assessing
0:01:55how sensitive and different automatic accent recognition systems are
0:02:00a combination of text-dependent in text-independent systems and the how robust these things can be
0:02:07that this problem features that's challenges these systems in
0:02:13in different steps
0:02:14thank you