N-gram Adaptation with Dynamic Interpolation Coefficient Using Information Retrieval Technique

Joon-Ki CHOI  Yung-Hwan OH  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E89-D   No.9   pp.2579-2582
Publication Date: 2006/09/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.9.2579
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Speech and Hearing
Keyword: 
language model adaptation,  adaptation corpus,  dynamic interpolation coefficient,  speech recognition,  

Full Text: PDF(210.5KB)>>
Buy this Article




Summary: 
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.