Generating Exact Lattices in The WFST Framework
| Type of publication: | Conference paper |
| Citation: | Povey_ICASSP_2012 |
| Publication status: | Published |
| Booktitle: | Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing. |
| Year: | 2012 |
| Month: | May |
| Pages: | 4213-4216 |
| Publisher: | IEEE Signal Processing Societ |
| Location: | Kyoto, Japan |
| Organization: | The 37th International Conference on Acoustics, Speech, and Signal Processing, Kyoto, JP |
| ISBN: | 978-1-4673-0044-5 |
| DOI: | 10.1109/ICASSP.2012.6288848 |
| Abstract: | We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alterna- tive transcriptions of an utterance. This method does not introduce substantial overhead above one-best decoding. Our method is most directly applicable when using WFST decoders where the WFST is “fully expanded”, i.e. where the arcs correspond to HMM transi- tions. It outputs lattices that include HMM-state-level alignments as well as word labels. The general idea is to create a state-level lattice during decoding, and to do a special form of determinization that retains only the best-scoring path for each word sequence. This spe- cial determinization algorithm is a solution to the following problem: Given a WFST A, compute a WFST B that, for each input-symbol- sequence of A, contains just the lowest-cost path through A. |
| Keywords: | |
| Projects: |
Idiap |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
