LET-Decoder: A WFST-Based Lazy-Evaluation Token-Group Decoder With Exact Lattice Generation
| Autor: | Mahsa Yarmohammadi, Daniel Povey, Hang Lv, Li Ke, Lei Xie, Yiming Wang, Sanjeev Khudanpur |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
Applied Mathematics Frame (networking) 020206 networking & telecommunications 02 engineering and technology Security token Token passing Signal Processing 0202 electrical engineering electronic engineering information engineering Overhead (computing) Electrical and Electronic Engineering Lazy evaluation Hidden Markov model Algorithm Word (computer architecture) Decoding methods |
| Zdroj: | IEEE Signal Processing Letters. 28:703-707 |
| ISSN: | 1558-2361 1070-9908 |
| DOI: | 10.1109/lsp.2021.3067220 |
| Popis: | We propose a novel lazy-evaluation token-group decoding algorithm with on-the-fly composition of weighted finite-state transducers (WFSTs) for large vocabulary continuous speech recognition. In the standard on-the-fly composition decoder, a base WFST and one or more incremental WFSTs are composed during decoding, and then token passing algorithm is employed to generate the lattice on the composed search space, resulting in substantial computation overhead. To improve speed, the proposed algorithm adopts 1) a token-group method, which groups tokens with the same state in the base WFST on each frame and limits the capacity of the group and 2) a lazy-evaluation method, which does not expand a token group and its source token groups until it processes a word label during decoding. Experiments show that the proposed decoder works notably up to 3 times faster than the standard on-the-fly composition decoder. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|