A comparison of two LVR search optimization techniques

Stephan Kanthak, Hermann Ney, Michael Riley, Mehryar Mohri

Research output: Contribution to conferencePaper

Abstract

This paper presents a detailed comparison between two search optimization techniques for large vocabulary speech recognition - one based on word-conditioned tree search (WCTS) and one based on weighted finite-state transducers (WFSTs). Existing North American Business News systems from RWTH and AT&T representing each of the two approaches, were modified to remove variations in model data and acoustic likelihood computation. An experimental comparison showed that the WFST-based system explored fewer search states and had less runtime overhead than the WCTS-based system for a given word error rate. This is attributed to differences in the pre-compilation, degree of non-determinism, and path weight distribution in the respective search graphs.

Original languageEnglish (US)
Pages1309-1312
Number of pages4
StatePublished - Jan 1 2002
Event7th International Conference on Spoken Language Processing, ICSLP 2002 - Denver, United States
Duration: Sep 16 2002Sep 20 2002

Other

Other7th International Conference on Spoken Language Processing, ICSLP 2002
CountryUnited States
CityDenver
Period9/16/029/20/02

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint Dive into the research topics of 'A comparison of two LVR search optimization techniques'. Together they form a unique fingerprint.

  • Cite this

    Kanthak, S., Ney, H., Riley, M., & Mohri, M. (2002). A comparison of two LVR search optimization techniques. 1309-1312. Paper presented at 7th International Conference on Spoken Language Processing, ICSLP 2002, Denver, United States.