Speech Recognition on DIRHA English WSJ
Metric: Word Error Rate (WER) (lower is better)
Metric: Word Error Rate (WER) (lower is better)
| # | Model↕ | Word Error Rate (WER)▲ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Li-GRU | 23.9 | No | The PyTorch-Kaldi Speech Recognition Toolkit | 2018-11-19 | Code |
| 2 | PASE-FineTuned | 29.8 | No | Learning Problem-agnostic Speech Representations... | 2019-04-06 | Code |
| 3 | SincNet-Raw waveform | 38.2 | No | Interpretable Convolutional Filters with SincNet | 2018-11-23 | Code |