Table 3 False rejection rates for OOV words when using Julius-based ASR
From: Dynamic out-of-vocabulary word registration to language model for speech recognition
Position | Freq. | 2 mora | 3 mora | 4 mora | 5 mora | |
|---|---|---|---|---|---|---|
ONE | – | – | .964 | .106 | .143 | .044 |
ALL | – | – | .506 | .128 | .071 | .022 |
500r | Random | 500 | .602 | .138 | .089 | .022 |
1kr | Random | 1000 | .566 | .128 | .071 | .022 |
2kr | Random | 2000 | .422 | .117 | .071 | .022 |
5kr | Random | 5000 | .349 | .096 | .089 | .022 |
500c | POS | 500 | .590 | .128 | .071 | .022 |
1kc | POS | 1000 | .458 | .096 | .054 | .022 |
2kc | POS | 2000 | .349 | .117 | .054 | .044 |
5kc | POS | 5000 | .313 | .085 | .071 | 0 |