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 | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
