Speech Recognition On Wsj Dev93
Metrics
Word Error Rate (WER)
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| Convolutional Speech Recognition | 6.8 | Fully Convolutional Speech Recognition |
| Convolutional Speech Recognition | 6.23 | CRF-based Single-stage Acoustic Modeling with CTC Topology |
| CTC-CRF VGG-BLSTM | 5.7 | CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency |
| CTC-CRF ST-NAS | 5.68 | Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients |
0 of 4 row(s) selected.