Reliable feature selection for language model adaptation

Chuang Hua Chueh*, Jen-Tzung Chien

*Corresponding author for this work

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

3 Scopus citations

Abstract

Language model adaptation aims to adapt a general model to a domain-specific model so that the adapted model can match the lexical information in test data. The minimum discrimination information (MDI) is a popular mechanism for language model adaptation through minimizing the Kullback-Leibler distance to the background model where the constraints found in adaptation data are satisfied. MDI adaptation with unigram constraints has been successfully applied for speech recognition owing to its computational efficiency. However, the unigram features only contain low-level information of adaptation articles which are too rough to attain precise adaptation performance. Accordingly, it is desirable to induce high-order features and explore delicate information for language model adaptation if the adaptation data is abundant. In this study, we focus on adaptively select the reliable features based on re-sampling and calculating the statistical confidence interval. We identify the reliable regions and build the inequality constraints for MDI adaptation. In this way, the reliable intervals can be used for adaptation so that interval estimation is achieved rather than point estimation. Also, the features can be selected automatically in the whole procedure. In the experiments, we carry out the proposed method for broadcast news transcription. We obtain significant improvement compared to conventional MDI adaptation with unigram features for different amount of adaptation data.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages5089-5092
Number of pages4
DOIs
StatePublished - 16 Sep 2008
Event2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States
Duration: 31 Mar 20084 Apr 2008

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
CountryUnited States
CityLas Vegas, NV
Period31/03/084/04/08

Keywords

  • Confidence Interval
  • Feature Selection
  • Language Model
  • Minimum Discrimination Information
  • Speech Recognition

Fingerprint Dive into the research topics of 'Reliable feature selection for language model adaptation'. Together they form a unique fingerprint.

  • Cite this

    Chueh, C. H., & Chien, J-T. (2008). Reliable feature selection for language model adaptation. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (pp. 5089-5092). [4518803] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4518803