CNN on MFSC/fbanks + 1 non-conv layer for FMLLR/I-Vectors concatenated in a DNN
Reported on 1 benchmark across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Audio1 result
- Percentage error10.4best: 4.3 (IBM (LSTM+Conformer encoder-decoder))