Fast N-Gram Language Model Look-Ahead for Decoders With Static Pronunciation Prefix Trees

Share/Save/Bookmark

Huijbregts, Marijn and Ordelman, Roeland and Jong, Franciska de (2008) Fast N-Gram Language Model Look-Ahead for Decoders With Static Pronunciation Prefix Trees. In: Interspeech 2008, 22-26 September 2008, Brisbane, Australia.

open access
[img]
Preview
PDF
162kB
Abstract:Decoders that make use of token-passing restrict their search space by various types of token pruning. With use of the Language Model Look-Ahead (LMLA) technique it is possible to increase the number of tokens that can be pruned without loss of decoding precision. Unfortunately, for token passing decoders that use single static pronunciation prefix trees, full n-gram LMLA increases the needed number of language model probability calculations considerably. In this paper a method for applying full n-gram LMLA in a decoder with a single static pronunciation tree is introduced. The experiments show that this method improves the speed of the decoder without an increase of search errors.
Item Type:Conference or Workshop Item
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/65373
Conference URL:http://www.isca-speech.org/archive/interspeech_2008/
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page

Metis ID: 255484