GTM-UVigo Contrastive (eval)

Reported on 3 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech3 results

Keyword SpottingonQUESST
Cnxe
0.999
best: 6.0905 (NNI non-filtered(for the development set))
Keyword SpottingonQUESST
MinCnxe
0.923
best: 0.9872 (CUNY [SMO+iSAX] (dev))
Keyword SpottingonQUESST
lowerbound
0.633
best: 0.592 (GTM-UVigo Primary late submission (eval))