Show simple item record

dc.contributor.authorLyon, C.en_US
dc.contributor.authorDickerson, R.en_US
dc.date.accessioned2008-02-28T10:02:58Z
dc.date.available2008-02-28T10:02:58Z
dc.date.issued1999en_US
dc.identifier.citationIn: Procs of 5th Natural Language Processing Pacific Rim Symposiumen_US
dc.identifier.other901891en_US
dc.identifier.urihttp://hdl.handle.net/2299/1696
dc.description.abstractCharacteristics of natural language can be illuminated through the application of well known tools in Information Theory. This paper shows how some of these characteristics can be exploited in the development of automated speech and language processing applications. The explicit representation of discontinuities in a temporal sequence of sounds, such as pauses in speech, can be utilized to improve the transmission of information. Arguments based on comparative entropy measures are used.en
dc.format.extent170845 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherChinese Information Processing Society of Chinaen_US
dc.titleExploiting statistical characteristics of word sequences for the efficient coding of speech.en_US
dc.typeConference paperen_US
herts.preservation.rarelyaccessedtrue


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record