Show simple item record

dc.contributor.authorFrankel, Joeen
dc.contributor.authorWester, Mirjamen
dc.contributor.authorKing, Simonen
dc.date.accessioned2007-09-18T09:58:40Z
dc.date.available2007-09-18T09:58:40Z
dc.date.issued2007
dc.identifier.citationJ. Frankel, M. Wester, and S. King. Articulatory feature recognition using dynamic Bayesian networks. Computer Speech & Language, 21(4):620-640, October 2007.
dc.identifier.urihttp://hdl.handle.net/1842/1991
dc.description.abstractWe describe a dynamic Bayesian network for articulatory feature recognition. The model is intended to be a component of a speech recognizer that avoids the problems of conventional ``beads-on-a-string'' phoneme-based models. We demonstrate that the model gives superior recognition of articulatory features from the speech signal compared with a state of- the art neural network system. We also introduce a training algorithm that offers two major advances: it does not require time-aligned feature labels and it allows the model to learn a set of asynchronous feature changes in a data-driven manner.en
dc.format.extent1782888 bytesen
dc.format.mimetypeapplication/pdfen
dc.language.isoen
dc.subjectspeech technologyen
dc.titleArticulatory feature recognition using dynamic Bayesian networks.en
dc.typeArticleen


Files in this item

This item appears in the following Collection(s)

Show simple item record