0:00:15my little posters about forensic voice comparison
0:00:21and it's
0:00:23takes some examples from real casework to describe
0:00:29a small experiment to find out
0:00:32what might be a slightly better way of doing things because as i've written here
0:00:37when we do
0:00:38real world forensic voice comparison
0:00:41we want to know what the best approaches to use on the circumstances of the
0:00:48and this is really the
0:00:52main reason for doing this kind of research simply to find out when you've got
0:00:57of the case the that the case in front of you
0:01:01what's the best
0:01:02approach to use
0:01:05it's deals with the situation way you have recurrent probably syllabic words like alright crops
0:01:13up a lot not too bad crops up a lot hello okay
0:01:17in both suspect and offender speech samples
0:01:21if you are using semi
0:01:23semi automatic forensic
0:01:26speaker recognition methods then a one of the main things that is the model they
0:01:30the performance
0:01:33trajectories on the separate syllables like and i
0:01:39but what i wanted to do was to find out whether you get better strength
0:01:43of evidence
0:01:44if you don't do that but measure of the formant trajectories over the whole of
0:01:49the work
0:01:50a sort of a kind of so to perform well that it from multiple
0:01:54so that this was tested with some high-level features
0:01:59from thee formant a pattern and the tonal fundamental frequency in the cantonese would die
0:02:05which means first
0:02:08and validated we'd likelihood ratios
0:02:11so i obviously there's absolutely nothing whatsoever i can
0:02:16side you about automatic speaker recognition i realise that but they might be some
0:02:20interesting aspects
0:02:23concerning the simple a high-level will to the that we that we working and i
0:02:29do have some interesting things to say that likelihood ratios which you might want to
0:02:33come check with me about and
0:02:37the main reason on here goes is to is to how you can help me
0:02:41out so please come have a chat thank you