2D ConvNet with Attention and GRU(MixUp=NO)

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Speech2 results

DialogueonVoxForge European
Accuracy (%)· 2019-10-09
94.7
best: 96.3 (2D ConvNet(MixUp=YES))
Spoken Language Identification using ConvNets arXiv:1910.04269
Spoken Language UnderstandingonVoxForge European
Accuracy (%)· 2019-10-09
94.7
best: 96.3 (2D ConvNet(MixUp=YES))
Spoken Language Identification using ConvNets arXiv:1910.04269

Natural Language Processing1 result

Dialogue UnderstandingonVoxForge European
Accuracy (%)· 2019-10-09
94.7
best: 96.3 (2D ConvNet(MixUp=YES))
Spoken Language Identification using ConvNets arXiv:1910.04269