A Generalized Dynamic Composition Algorithm of Weighted Finite State Transducers for Large Vocabulary Speech Recognition

Report English OPEN
Cheng, Octavian; Dines, John; Magimai.-Doss, Mathew;
(2006)
  • Publisher: IDIAP

We propose a generalized dynamic composition algorithm of weighted finite state transducers (WFST), which avoids the creation of non-coaccessible paths, performs weight look-ahead and does not impose any constraints to the topology of the WFSTs. Experimental results on ... View more
Share - Bookmark