Integrating detailed information into a language model

Ruiqiang Zhang, Ezra Black, Andrew Finch, Yoshinori Sagisaka

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

6 Citations (Scopus)

Abstract

Applying natural language processing technique to language modeling is a key problem in speech recognition. This paper describes a maximum entropy-based approach to language modeling in which both words together with syntactic and semantic tags in the long history are used as a basis for complex linguistic questions. These questions are integrated with a standard trigram language model or a standard trigram language model combined with long history word triggers and the resulting language model is used to rescore the N-best hypotheses output of the ATRSPREC speech recognition system. The technique removed 24% of the correctable error of the recognition system.

Original languageEnglish
Title of host publicationSpeech Processing II
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1595-1598
Number of pages4
ISBN (Electronic)0780362934
DOIs
Publication statusPublished - 2000 Jan 1
Event25th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000 - Istanbul, Turkey
Duration: 2000 Jun 52000 Jun 9

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume3
ISSN (Print)1520-6149

Conference

Conference25th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000
CountryTurkey
CityIstanbul
Period00/6/500/6/9

    Fingerprint

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Zhang, R., Black, E., Finch, A., & Sagisaka, Y. (2000). Integrating detailed information into a language model. In Speech Processing II (pp. 1595-1598). [861995] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2000.861995