Table 3 Recognition performance of second-pass re-scoring
From: A hybrid input-type recurrent neural network for LVCSR language modeling
Tasks | LM | 4gr | RNNLMs | ||||
|---|---|---|---|---|---|---|---|
| Â | Â | s-H | W | PM | H-F | H-R1 | H-R2 |
| Â | #Word | 30 K | 35 K | 0 K | 35 K | 30 K | 25 K |
| Â | #PM | 21 K | 0 K | 25 K | 25 K | 5 K | 10 K |
BN | PER (%) | 19.60 | 19.11 | 19.12 | 18.73 | 18.84 | 18.81 |
| Â | WER (%) | 22.92 | 22.22 | 22.23 | 22.05 | 22.16 | 22.13 |
VT | PER (%) | 19.02 | 19.02 | 19.26 | 18.89 | 18.79 | 18.41 |
| Â | WER (%) | 21.75 | 21.85 | 22.17 | 21.69 | 21.57 | 21.27 |
AVG. | PER (%) | 19.31 | 19.07 | 19.19 | 18.81 | 18.82 | 18.61 |
| Â | WER (%) | 22.34 | 22.04 | 22.20 | 21.87 | 21.87 | 21.70 |