2 search results - page 1 / 1 » 3-Way Composition of Weighted Finite-State Transducers |
CORR
2008
Springer
13 years 6 months ago
2008
Springer
ICASSP
2009
IEEE
14 years 2 months ago
2009
IEEE
In the Weighted Finite State Transducer (WFST) framework for speech recognition, we can reduce memory usage and increase flexibility by using on-the-fly composition which genera...