Deep CNN (10 conv, 4 FC layers), multi-scale feature maps
Reported on 1 benchmark across 1 task · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Audio1 result
- Percentage error· 2015-09-2912.2best: 4.3 (IBM (LSTM+Conformer encoder-decoder))