Publication Details
Combination of strongly and weakly constrained recognizers for reliable detection of OOVs
Schwarz Petr, Ing., Ph.D. (DCGM)
Matějka Pavel, Ing., Ph.D. (DCGM)
Hannemann Mirko, Ph.D.
Rastrow Ariya
White Christopher
Khudanpur Sanjeev
Heřmanský Hynek, prof. Ing., Dr. Eng. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
speech processing, speech recognition, OOV detection, utterance verification
The paper is on the description of combination of strongly and weakly constrained recognizers for reliable detection of OOVs.
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 word- and 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.
@inproceedings{BUT27762,
author="Lukáš {Burget} and Petr {Schwarz} and Pavel {Matějka} and Mirko {Hannemann} and Ariya {Rastrow} and Christopher {White} and Sanjeev {Khudanpur} and Hynek {Heřmanský} and Jan {Černocký}",
title="Combination of strongly and weakly constrained recognizers for reliable detection of OOVs",
booktitle="Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP)",
year="2008",
pages="1--4",
publisher="IEEE Signal Processing Society",
address="Las Vegas",
isbn="1-4244-1484-9",
url="http://www.fit.vutbr.cz/research/groups/speech/publi/2008/oov_icassp2008_final.pdf"
}