Table 8 WER% of Nevisa on small and large Farsdat using context-independent (phone) and context-dependent (triphone) modeling
From: A large vocabulary continuous speech recognition system for Persian language
Train | Test | ||
|---|---|---|---|
Databse | Context | gFarsdat | sFarsdat |
sFarsdat | Independent | 29.60 | 25.77 |
sFarsdat | Dependent | 20.51 | 16.79 |
gFarsdat | Independent | 6.10 | 37.39 |
gFarsdat | Dependent | 5.21 | 26.85 |