N-gram adaptation with dynamic interpolation coefficient using information retrieval technique

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 734
  • Download : 522
This study presents an N-gram adaptation technique when additional text data for the adaptation do not exist. We use a language modeling approach to the information retrieval (IR) technique to collect the appropriate adaptation corpus from baseline text data. We propose to use a dynamic interpolation coefficient to merge the N-gram, where the interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech. Experimental results show that the proposed adapted N-gram always has better performance than the background N-gram.
Publisher
IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
Issue Date
2006-09
Language
English
Article Type
Article
Citation

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E89D, no.9, pp.2579 - 2582

ISSN
0916-8532
DOI
10.1093/ietisy/e89-d.9.2579
URI
http://hdl.handle.net/10203/17279
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
000240524000012.pdf(212.5 kB)Download

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0