Speech Recognition on CHiME clean
Metric: Percentage error (lower is better)
Metric: Percentage error (lower is better)
| # | Model↕ | Percentage error▲ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Deep Speech 2 | 3.34 | No | Deep Speech 2: End-to-End Speech Recognition in ... | 2015-12-08 | Code |
| 2 | CNN + Bi-RNN + CTC (speech to letters) | 6.3 | No | Deep Speech: Scaling up end-to-end speech recogn... | 2014-12-17 | Code |