Show simple item record

dc.contributor.authorGutkin, Alexander
dc.contributor.authorGay, David R
dc.contributor.authorGoldfarb, Lev
dc.contributor.authorWester, Mirjam
dc.coverage.spatial20en
dc.date.accessioned2006-05-10T17:35:26Z
dc.date.available2006-05-10T17:35:26Z
dc.date.issued2004-08
dc.identifier.citationProc. Workshop on Pattern Representation and the Future of Pattern Recognition (17th International Conference on Pattern Recognition), (L. Goldfarb, ed.) Cambridge, UK (2004) pp. 57–76en
dc.identifier.urihttp://hdl.handle.net/1842/967
dc.description.abstractThis paper deals with the formulation of an alternative, structural, approach to the speech representation and recognition problem. In this approach, we require both the representation and the learning algorithms to be linguistically meaningful and to naturally represent the linguistic data at hand. This allows the speech recognition system to discover the emergent combinatorial structure of the linguistic classes. The proposed approach is developed within the ETS formalism, the first formalism in applied mathematics specifically designed to address the issues of class and object/event representation. We present an initial application of ETS to the articulatory modelling of speech based on elementary physiological gestures that can be reliably represented as the ETS primitives. We discuss the advantages of this gestural approach over prevalent methods and its promising potential to mathematical modelling and representation in linguistics.en
dc.format.extent464261 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.titleOn the Articulatory Representation of Speech within the Evolving Transformation System Formalismen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record