Structural bayesian language modeling and adaptation

Sibel Yaman*, Jen-Tzung Chien, Chin Hui Lee

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

We propose a language modeling and adaptation framework using Bayesian structural maximum a posteriori (SMAP) principle, in which each η-gram event is embedded in a branch of a tree structure. The nodes in the first layer of this tree structure represent the unigrams, and those in the second layer represent the bigrams, and so on. Each node in the tree structure has an associated hyper-parameter representing the information about the prior distribution, and a count representing the number of times the word sequence occurs in the domain-specific data. In general, the hyper-parameters depend on the observation frequency of not only the node event but also its parent node of lower order n-gram event. Our automatic speech recognition experiments using the Wall Street Journal corpus verify that the proposed SMAP language model adaptation achieves a 5.6% relative improvement over maximum likelihood language models obtained with the same training and adaptation data sets.

Original languageEnglish
Title of host publicationInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Pages2476-2479
Number of pages4
StatePublished - 1 Dec 2007
Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, Belgium
Duration: 27 Aug 200731 Aug 2007

Publication series

NameInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Volume4

Conference

Conference8th Annual Conference of the International Speech Communication Association, Interspeech 2007
CountryBelgium
CityAntwerp
Period27/08/0731/08/07

Keywords

  • Automatic speech recognition and understanding
  • Bayesian language modeling
  • Bayesian learning
  • Language model adaptation

Fingerprint Dive into the research topics of 'Structural bayesian language modeling and adaptation'. Together they form a unique fingerprint.

Cite this