File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Neural network model of binaural hearing based on spatial feature extraction of the head related transfer function

TitleNeural network model of binaural hearing based on spatial feature extraction of the head related transfer function
Authors
KeywordsSpatial Hearing
Feature Extraction
Neural Networks
Issue Date1998
PublisherIEEE.
Citation
The 20th IEEE Engineering in Medicine and Biology Society Conference Proceedings, Hong Kong, China, 29 October - 1 November 1998, v. 3, p. 1109-1112 How to Cite?
AbstractIn spatial hearing, complex valued head-related transfer function (HRTF) can be represented as a real valued head-related impulse response (HRIR). Using Karhunen-Loeve expansion, the spatial features of the normalized HRIRs on measurement space can be extracted as spatial character functions. A neural network model based on Von-Mises function is used to approximate the discrete spatial character function of HRIR. As a result, a time-domain binaural model is established and it fits the measured HRIRs well.
Persistent Identifierhttp://hdl.handle.net/10722/46119
ISSN

 

DC FieldValueLanguage
dc.contributor.authorWu, ZYen_HK
dc.contributor.authorWeng, Ten_HK
dc.contributor.authorWang, WBen_HK
dc.contributor.authorLo, TFen_HK
dc.contributor.authorChan, FHYen_HK
dc.contributor.authorLam, FKen_HK
dc.date.accessioned2007-10-30T06:42:56Z-
dc.date.available2007-10-30T06:42:56Z-
dc.date.issued1998en_HK
dc.identifier.citationThe 20th IEEE Engineering in Medicine and Biology Society Conference Proceedings, Hong Kong, China, 29 October - 1 November 1998, v. 3, p. 1109-1112en_HK
dc.identifier.issn1557-170Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/46119-
dc.description.abstractIn spatial hearing, complex valued head-related transfer function (HRTF) can be represented as a real valued head-related impulse response (HRIR). Using Karhunen-Loeve expansion, the spatial features of the normalized HRIRs on measurement space can be extracted as spatial character functions. A neural network model based on Von-Mises function is used to approximate the discrete spatial character function of HRIR. As a result, a time-domain binaural model is established and it fits the measured HRIRs well.en_HK
dc.format.extent254384 bytes-
dc.format.extent13817 bytes-
dc.format.extent8841 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.subjectSpatial Hearingen_HK
dc.subjectFeature Extractionen_HK
dc.subjectNeural Networksen_HK
dc.titleNeural network model of binaural hearing based on spatial feature extraction of the head related transfer functionen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1557-170X&volume=3&spage=1109&epage=1112&date=1998&atitle=Neural+network+model+of+binaural+hearing+based+on+spatial+feature+extraction+of+the+head+related+transfer+functionen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/IEMBS.1998.747065en_HK
dc.identifier.hkuros45231-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats