Combination of Strongly and Weakly Constrained Recognizers for Reliable Detection of OOVs”, ICASSP (2008)
| Citations: | 8 - 3 self |
BibTeX
@MISC{Schwarz08combinationof,
author = {Petr Schwarz and Pavel Matějka and Mirko Hannemann and Ariya Rastrow and Christopher White and Sanjeev Khudanpur and Hynek Hermansky},
title = {Combination of Strongly and Weakly Constrained Recognizers for Reliable Detection of OOVs”, ICASSP},
year = {2008}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper addresses the detection of OOV segments in the output of large vocabulary continuous speech recognition (LVCSR) system. First, standard confidence measures based on frame-based wordand phone- posteriors are investigated. Substantial improvement was however obtained when posteriors from two systems- strongly constrained (LVCSR) and weakly constrained (phone posterior estimator) were combined. We show that this approach is suitable also for the detection of general recognition errors. All the results are presented on WSJ task with reduced recognition vocabulary. Index Terms — LVCSR, OOV, confidence measures. 1.
