Incorporating proximity information for relevance language modeling in speech recognition

Yi Wen Chen, Bo Han Hao, Kuan Yu Chen, Berlin Chen

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

Language modeling (LM), aiming to provide a statistical mechanism to associate quantitative scores to sequences of words, has long been an interesting yet challenging problem in the field of speech and language processing. Although the ngram model remains the predominant one, a number of disparate LM methods have been developed to complement the n-gram model. Among them, relevance modeling (RM) that explores the relevance information inherent between the search history and an upcoming word has shown preliminary promise for dynamic language model adaptation. This paper continues this general line of research in two significant aspects. First, the so-called "bag-of- words" assumption of RM is relaxed by incorporating word proximity evidence into the RM formulation. Second, latent topic information is additionally explored in the hope to further enhance the proximity-based RM framework. A series of experiments conducted on a large vocabulary continuous speech recognition (LVCSR) task seem to demonstrate that the various language models deduced from our framework are very comparable to existing language models.

Original languageEnglish
Pages (from-to)2683-2687
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2013 Jan 1
Event14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013 - Lyon, France
Duration: 2013 Aug 252013 Aug 29

    Fingerprint

Keywords

  • Language model
  • Latent topic information
  • Proximity evidence
  • Relevance model
  • Speech recognition

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this