Effective pseudo-relevance feedback for language modeling in speech recognition

Berlin Chen, Yi Wen Chen, Kuan Yu Chen, Ea Ee Jan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A part and parcel of any automatic speech recognition (ASR) system is language modeling (LM), which helps to constrain the acoustic analysis, guide the search through multiple candidate word strings, and quantify the acceptability of the final output hypothesis given an input utterance. Despite the fact that the n-gram model remains the predominant one, a number of novel and ingenious LM methods have been developed to complement or be used in place of the n-gram model. A more recent line of research is to leverage information cues gleaned from pseudo-relevance feedback (PRF) to derive an utterance-regularized language model for complementing the n-gram model. This paper presents a continuation of this general line of research and its main contribution is two-fold. First, we explore an alternative and more efficient formulation to construct such an utterance-regularized language model for ASR. Second, the utilities of various utterance-regularized language models are analyzed and compared extensively. Empirical experiments on a large vocabulary continuous speech recognition (LVCSR) task demonstrate that our proposed language models can offer substantial improvements over the baseline n-gram system, and achieve performance competitive to, or better than, some state-of-the-art language models.

Original languageEnglish
Title of host publication2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings
Pages13-18
Number of pages6
DOIs
Publication statusPublished - 2013 Dec 1
Event2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Olomouc, Czech Republic
Duration: 2013 Dec 82013 Dec 13

Publication series

Name2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings

Other

Other2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013
CountryCzech Republic
CityOlomouc
Period13/12/813/12/13

    Fingerprint

Keywords

  • Speech recognition
  • information retrieval
  • language modeling
  • pseudo-relevance feedback
  • relevance

ASJC Scopus subject areas

  • Speech and Hearing

Cite this

Chen, B., Chen, Y. W., Chen, K. Y., & Jan, E. E. (2013). Effective pseudo-relevance feedback for language modeling in speech recognition. In 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings (pp. 13-18). [6707698] (2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings). https://doi.org/10.1109/ASRU.2013.6707698