Speech Enhancement on TCD-TIMIT 2 Speakers (test)
10.55SDRAV c-ref
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| AV c-reftype=Speaker-independent, features=Landmark motion vectors, talkers=22018.11 | 10.55 | 3.03 | 3.21 | |
| AV concattype=Speaker-independent, features=Landmark motion vectors, talkers=22018.11 | 9.56 | 2.8 | 3.09 | |
| VL2M_reftype=Speaker-independent, features=Landmark motion vectors, talkers=22018.11 | 9.24 | 2.81 | 3.09 | |
| VL2Mtype=Speaker-independent, features=Landmark motion vectors, talkers=22018.11 | 2.88 | 2.25 | 2.62 | |
| Noisytype=Input mixed-speech signal, talkers=22018.11 | 0.21 | 2.22 | 2.74 |