Noisy Speech Recognition On Chime Real
評価指標
Percentage error
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Percentage error | Paper Title | Repository |
|---|---|---|---|
| CNN + Bi-RNN + CTC (speech to letters) | 67.94 | Deep Speech: Scaling up end-to-end speech recognition | |
| HMM-TDNN(LFMMI) + LSTMLM | 11.4 | Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline | - |
| Deep Speech 2 | 21.79 | Deep Speech 2: End-to-End Speech Recognition in English and Mandarin | |
| Li-GRU | 14.6 | The PyTorch-Kaldi Speech Recognition Toolkit | |
| Distortion-Independent + WRBN + Utterance-Wise Recurrent Dropout + Magnitude Features | 7.8 | - | - |
0 of 5 row(s) selected.