Show simple item record

Exploiting Sequential Phonetic Constraints in Recognizing Spoken Words

dc.date.accessioned2004-10-04T14:56:14Z
dc.date.accessioned2018-11-24T10:13:36Z
dc.date.available2004-10-04T14:56:14Z
dc.date.available2018-11-24T10:13:36Z
dc.date.issued1985-10-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/6434
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/6434
dc.description.abstractMachine recognition of spoken language requires developing more robust recognition algorithms. The current paper extends the work of Shipman and Zue by investigating the power of partial phonetic descriptions. First we demonstrate that sequences of manner of articulation classes are more reliable and provide more constraint than other classes. Alone these are of limited utility, due to the high degree of variability in natural speech. This variability is not uniform, however, as most modifications and deletions occur in unstressed syllables. The stressed syllables provide substantially more constraint. This indicates that recognition algorithms can be made more robust by exploiting the manner of articulation information in stressed syllables.en_US
dc.format.extent3921047 bytes
dc.format.extent1455850 bytes
dc.language.isoen_US
dc.titleExploiting Sequential Phonetic Constraints in Recognizing Spoken Wordsen_US


Files in this item

FilesSizeFormatView
AIM-867.pdf1.455Mbapplication/pdfView/Open
AIM-867.ps3.921Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record