Conference paper

KOMBRINK Stefan, HANNEMANN Mirko, BURGET Lukáš and HEŘMANSKÝ Hynek. Recovery of Rare Words in Lecture Speech. In: Proc. Text, Speech and Dialogue 2010. Brno: Springer Verlag, 2010, pp. 330-337. ISBN 978-3-642-15759-2. ISSN 0302-9743.
Publication language:english
Original title:Recovery of Rare Words in Lecture Speech
Title (cs):Obnova řídkých slov v rozpoznávání řeči z přednášek
Pages:330-337
Proceedings:Proc. Text, Speech and Dialogue 2010
Conference:13th International Conference on Text, Speech and Dialogue, TSD 2010
Place:Brno, CZ
Year:2010
ISBN:978-3-642-15759-2
Journal:Lecture Notes in Computer Science, Vol. 2010, No. 9, DE
ISSN:0302-9743
Publisher:Springer Verlag
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2010/kombrink_TSD_2010_330.pdf [PDF]
Keywords
speech, rare words, recognizer, detect OOV words, sub-words, lectures
Annotation
This paper is on recovery of rare words in lecture speech. We use a hybrid word/sub-word recognizer to detect OOV words occurring in English talks and describe them as sequences of sub-words.
Abstract
The vocabulary used in speech usually consists of two types of words: a limited set of common words, shared across multiple documents, and a virtually unlimited set of rare words, each of which might appear a few times only in particular documents. In most documents, however, these rare words are not seen at all. The first type of words is typically included in the language model of an automatic speech recognizer (ASR) and is thus widely referred to as invocabulary (IV). Words of the second type are missing in the language model and thus are called out-of-vocabulary (OOV). However, these words usually carry important information. We use a hybrid word/sub-word recognizer to detect OOV words occurring in English talks and describe them as sequences of sub-words.We detected about one third of all OOV words, and were able to recover the correct spelling for 26.2% of all detections by using a phoneme-to-grapheme (P2G) conversion trained on the recognition dictionary. By omitting detections corresponding to recovered IV words, we were able to increase the precision of the OOV detection substantially
BibTeX:
@INPROCEEDINGS{
   author = {Stefan Kombrink and Mirko Hannemann and Luk{\'{a}}{\v{s}}
	Burget and Hynek He{\v{r}}mansk{\'{y}}},
   title = {Recovery of Rare Words in Lecture Speech},
   pages = {330--337},
   booktitle = {Proc. Text, Speech and Dialogue 2010},
   journal = {Lecture Notes in Computer Science},
   volume = {2010},
   number = {9},
   year = {2010},
   location = {Brno, CZ},
   publisher = {Springer Verlag},
   ISBN = {978-3-642-15759-2},
   ISSN = {0302-9743},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9323}
}

Your IPv4 address: 50.16.97.96
Switch to IPv6 connection

DNSSEC [dnssec]