| 0:00:15 | a lot easier or a improving the robustness of speaker verification systems against maybe speech |
|---|
| 0:00:23 | then i'll |
|---|
| 0:00:24 | tested with a |
|---|
| 0:00:26 | the original voice of the impose that the speaker state-of-the-art speaker verification systems perform better |
|---|
| 0:00:32 | but that the impersonator is mimicking the target speaker the performance deteriorates significantly |
|---|
| 0:00:42 | be addressed this issue you know in our work |
|---|
| 0:00:46 | we use a proximal support vector machine based backend classifier its use i-vectors that input |
|---|
| 0:00:52 | for improving the robustness against a mimicked speech |
|---|
| 0:00:58 | then be devised as tight as it do maybe each of the training examples for |
|---|
| 0:01:04 | this em to further improve the robustness of the system against mimicry it's is the |
|---|
| 0:01:11 | or stuff that was not but you |
|---|
| 0:01:14 | thank you |
|---|