| speech-recognition-on-swb-hub-500-wer | VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+Broadcast | – | Percentage error: 11.9 |
| speech-recognition-on-switchboard-hub500 | Microsoft 2016 | – | Percentage error: 6.2 |
| speech-recognition-on-switchboard-hub500 | RNNLM | – | Percentage error: 6.9 |
| speech-recognition-on-switchboard-hub500 | VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+Broadcast | – | Percentage error: 6.3 |