Audio samples and SED result for "Multi-channel separation of dynamic speech and sound events"
Authors: Takuya Fujimura, Robin Scheibler
Speech separation
moving-0/Example1
| Mixture |
|
| Target |
|
|
| TIV-IVA |
|
|
| ATT-IVA |
|
|
moving-0/Example2
| Mixture |
|
| Target |
|
|
| TIV-IVA |
|
|
| ATT-IVA |
|
|
moving-1/Example1
| Mixture |
|
| Target |
|
|
| TIV-IVA |
|
|
| ATT-IVA |
|
|
moving-1/Example2
| Mixture |
|
| Target |
|
|
| TIV-IVA |
|
|
| ATT-IVA |
|
|
moving-2/Example1
| Mixture |
|
| Target |
|
|
| TIV-IVA |
|
|
| ATT-IVA |
|
|
moving-2/Example2
| Mixture |
|
| Target |
|
|
| TIV-IVA |
|
|
| ATT-IVA |
|
|
SED with separation
Example1
| mix.wav |
|
| tiv_track0.wav |
|
| att_track0.wav |
|
Example2
| mix.wav |
|
| tiv_track3.wav |
|
| att_track0.wav |
|
Example3
| mix.wav |
|
| tiv_track1.wav |
|
| att_track2.wav |
|
Example4
| mix.wav |
|
| tiv_track1.wav |
|
| att_track2.wav |
|