Show simple item record

dc.contributor.authorGotoh, Yoshihiko
dc.contributor.authorRenals, Steve
dc.contributor.authorWilliams, Gethin
dc.date.accessioned2006-05-26T12:34:32Z
dc.date.available2006-05-26T12:34:32Z
dc.date.issued1999
dc.identifier.citationIn Proc IEEE ICASSP, pages 513-516, Phoenix AZ, 1999.en
dc.identifier.urihttp://hdl.handle.net/1842/1186
dc.description.abstractWe introduce Named Entity (NE) Language Modelling, a stochastic finite state machine approach to identifying both words and NE categories from a stream of spoken data. We provide an overview of our approach to NE tagged language model (LM) generation together with results of the application of such a LM to the task of out-of-vocabulary (OOV) word reduction in large vocabulary speech recognition. Using the Wall Street Journal and Broadcast News corpora, it is shown that the tagged LM was able to reduce the overall word error rate by 14%, detecting up to 70% of previously OOV words. We also describe an example of the direct tagging of spoken data with NE categories.en
dc.format.extent57111 bytes
dc.format.extent162753 bytes
dc.format.mimetypeapplication/octet-stream
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherIEEEen
dc.titleNamed entity tagged language models.en
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record