logo Idiap Research Institute        
 [BibTeX] [Marc21]
A Generalized Dynamic Composition Algorithm of Weighted Finite State Transducers for Large Vocabulary Speech Recognition
Type of publication: Idiap-RR
Citation: cheng:rr06-62
Number: Idiap-RR-62-2006
Year: 2006
Institution: IDIAP
Note: Submitted for publication
Abstract: 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 Wall Street Journal (WSJ1) 20k-word trigram task show that at 17\% WER (moderately-wide beam width,',','), the decoding time of the proposed approach is about 48\% and 65\% of the other two dynamic composition approaches. In comparison with static composition, at the same level of 17\% WER, we observe a reduction of about 60\% in memory requirement, with an increase of about 60\% in decoding time due to extra overheads for dynamic composition.
Userfields: ipdmembership={speech},
Keywords:
Projects Idiap
Authors Cheng, Octavian
Dines, John
Magimai.-Doss, Mathew
Added by: [UNK]
Total mark: 0
Attachments
  • cheng-idiap-rr-06-62.pdf
  • cheng-idiap-rr-06-62.ps.gz
Notes