Show simple item record

dc.contributor.authorPickersgill, C
dc.contributor.authorSo, Stephen
dc.contributor.authorSchwerin, B
dc.date.accessioned2019-05-03T00:00:57Z
dc.date.available2019-05-03T00:00:57Z
dc.date.issued2018
dc.identifier.issn2207-1296
dc.identifier.urihttp://hdl.handle.net/10072/383950
dc.description.abstractThis paper proposes a DNN-based preprocessing method for speech coding and automatic speech recognition applications. The method proposed here maps noisy log power spectra to “clean” smoothed log power spectral envelopes using DNN pre-diction. The proposed method has the advantage of combining feature extraction with DNN-based enhancement, thus reducing computational time and resources. The TIMIT speech database with various additive noise types was used to train the DNN, and the NN prediction results are compared to the target clean log power spectral envelopes using log spectral distortion. The proposed method is found to have lower log spectral distortion measurements compared to similar neural networks that map noisy power spectra to clean power spectra.
dc.description.peerreviewedYes
dc.publisherASSTA
dc.publisher.urihttp://sst2018.unsw.edu.au
dc.relation.ispartofconferencenameSST 2018
dc.relation.ispartofconferencetitle17th Speech Science and Technology Conference (SST2018)
dc.relation.ispartofdatefrom2018-12-04
dc.relation.ispartofdateto2018-12-07
dc.relation.ispartoflocationSydney, Australia
dc.subject.fieldofresearchSignal processing
dc.subject.fieldofresearchcode400607
dc.titleInvestigation of DNN Prediction of Power Spectral Envelopes for Speech Coding & ASR
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
dc.description.versionVersion of Record (VoR)
gro.rights.copyright© 2018 ASSTA. The attached file is reproduced here in accordance with the copyright policy of the publisher. Please refer to the conference's website for access to the definitive, published version.
gro.hasfulltextFull Text
gro.griffith.authorSo, Stephen
gro.griffith.authorSchwerin, Belinda M.


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record