Many-to-Many conversion samples from seen speakers

Description

We present the conversions generated by our method when converting seen speakers i.e. found in our method training data. For each conversion we display the source sample from the seen speaker, the generated sample and finally a sample recorded by the target speaker.

Conversions

Source Speaker ID Target Speaker ID Source Sample Generated Sample Target Speaker Example Sample
460 5778
5339 730
5339 1334
7800 8797
5322 2911
5393 6818
3486 911
2136 6367
2136 7505
6209 696
6000 1502
6000 7367
1578 6836
1355 5808
1116 5339
118 4362
4160 1069
4018 7113
887 3526
4214 200
1970 8630
6563 7800
2416 4813
6064 669
6064 6019
60 2092
6367 8312
5163 4137
5022 3983
1116 8014
40 2843
7078 5104
6529 250
2893 2416
1263 2817
730 8098
1841 3440
2836 6181
5163 4397
3983 6476
3983 3235
5022 7511
250 8051
7067 125
4640 3664
2836 83
1578 460
412 1098
5339 8238
8123 6272
6367 2893
6531 587
6367 1841
6272 8108
8226 27