Conference paper

WHITE Christopher, ZWEIG Geoffrey, BURGET Lukáš, SCHWARZ Petr and HEŘMANSKÝ Hynek. Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments. In: Proc. 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing. Las Vegas: IEEE Signal Processing Society, 2008, p. 4. ISBN 1-4244-1484-9.
Publication language:english
Original title:Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments
Title (cs):Odhad spolehlivosti, detekce OOV a identifikace jazyka pomocí transducerů převádějících fonémy na slova a fonetických zarovnání
Pages:4
Proceedings:Proc. 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing
Conference:33rd International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Place:Las Vegas, US
Year:2008
ISBN:1-4244-1484-9
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2008/white_icassp08.pdf [PDF]
Keywords
speech recognition
Annotation
the paper is on confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments
Abstract
Automatic Speech Recognition (ASR) systems continue to make errors during search when handling various phenomena including noise, pronunciation variation, and out of vocabulary (OOV) words. Predicting the probability that a word is incorrect can prevent the error from propagating and perhaps allow the system to recover. This paper addresses the problem of detecting errors and OOVs for read Wall Street Journal speech when the word error rate (WER) is very low. It augments a traditional confidence estimate by introducing two novel methods: phone-level comparison using Multi-String Alignment (MSA) and word-level comparison using phone-to-word transduction. We show that features from phone and word string comparisons can be added to a standard maximum entropy framework thereby substantially improving performance in detecting both errors and OOVs. Additionally we show an extension to detecting English and accented English for the Language Identification (LID) task.
BibTeX:
@INPROCEEDINGS{
   author = {Christopher White and Geoffrey Zweig and Luk{\'{a}}{\v{s}}
	Burget and Petr Schwarz and Hynek He{\v{r}}mansk{\'{y}}},
   title = {Confidence estimation, OOV detection and language ID using
	phone-to-word transduction and phone-level alignments},
   pages = {4},
   booktitle = {Proc. 2008 IEEE International Conference on Acoustics,
	Speech, and Signal Processing},
   year = {2008},
   location = {Las Vegas, US},
   publisher = {IEEE Signal Processing Society},
   ISBN = {1-4244-1484-9},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=8722}
}

Your IPv4 address: 54.225.3.114
Switch to IPv6 connection

DNSSEC [dnssec]