| 0:00:15 | good afternoon that would be present in the were carried out that the at the |
|---|
| 0:00:19 | university of mister |
|---|
| 0:00:21 | and i present in the age related voice disguise anything about speaker verification and as |
|---|
| 0:00:27 | we know when we ask that in the performance of a |
|---|
| 0:00:30 | of automatic speaker verification system we want to assess |
|---|
| 0:00:35 | inter speaker variability and we wanted to more |
|---|
| 0:00:38 | with h really that these guys and for that we define it that's the intentional |
|---|
| 0:00:43 | modification of the speaker voice sounded like the younger one and all the first and |
|---|
| 0:00:47 | so forth these we believe that the corpus with six stick speakers all native finnish |
|---|
| 0:00:52 | in that's to the environment and the speech is read text in finnish and in |
|---|
| 0:00:57 | english |
|---|
| 0:00:57 | and for these we got twenty six segments on each voiced i natural voice for |
|---|
| 0:01:02 | voicing your voice into different sessions for the speakers at the same time we do |
|---|
| 0:01:08 | the prior to recording with that too smart phones just to check this channel differences |
|---|
| 0:01:14 | also |
|---|
| 0:01:15 | and so we for the performance evaluation we use just a |
|---|
| 0:01:19 | mfcc feature fifty four dimensional and to a s p system base gmm ubm and |
|---|
| 0:01:26 | i-vector system with cosine and b lda score and ported that's there are we used |
|---|
| 0:01:31 | to going for the three conditions basically because we have one not recognition and then |
|---|
| 0:01:35 | the disguised condition would be different all and |
|---|
| 0:01:38 | own voice |
|---|
| 0:01:39 | we got this number of trials for each of these conditions and the channels as |
|---|
| 0:01:44 | i already mentioned so they training they that all these microphone data from the natural |
|---|
| 0:01:51 | voice and the corresponding disguised voice was used for testing in the in the disguise |
|---|
| 0:01:57 | conditions |
|---|
| 0:01:59 | so this is nick a big of the results and we can see for the |
|---|
| 0:02:03 | i-vector be lda a system we can see i degradation between the natural voice baseline |
|---|
| 0:02:10 | of the system and then they these guys all and these guys don't we can |
|---|
| 0:02:14 | see this degradation in for more details on the experimental setup and |
|---|
| 0:02:19 | the data please this poster seven |
|---|