Temporally Dynamic Neural Networks for Speaker Independent Phoneme Recognition

Simple item page
dc.contributor.advisorShamma, S.en_US
dc.contributor.authorEtemad, Kamranen_US
dc.contributor.departmentISRen_US
dc.date.accessioned2007-05-23T09:55:31Z
dc.date.available2007-05-23T09:55:31Z
dc.date.issued1993en_US
dc.description.abstractAn alternative view of neural network based phoneme recognition based on multiresolution signal processing which incorporates noncausal context is suggested. Also some suggestions are made regarding target and error weight functions to improve performance and simplify training. Based on these observations a temporally dynamic neural network with self recurrent links of different delays is suggested and tested on speaker independent unvoiced plosives, (p,t,k), recognition task with input feature vectors derived from an auditory model.en_US
dc.format.extent2798314 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/5460
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; MS 1993-17en_US
dc.subjectneural systemsen_US
dc.subjectspeech processingen_US
dc.subjectCommunication en_US
dc.subjectSignal Processing Systemsen_US
dc.titleTemporally Dynamic Neural Networks for Speaker Independent Phoneme Recognitionen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
MS_93-17.pdf
Size:
2.67 MB
Format:
Adobe Portable Document Format
Download

Collections

Institute for Systems Research Technical Reports