Show simple item record

dc.contributor.authorRoy, Sujan Kumar
dc.contributor.authorNicolson, Aaron
dc.contributor.authorPaliwal, Kuldip K
dc.description.abstractThe existing augmented Kalman filter (AKF) suffers from poor LPC estimates in real-world noise conditions, which degrades the speech enhancement performance. In this paper, a deep learning technique exploits the LPC estimates for the AKF to enhance speech in various noise conditions. Specifically, a deep residual network is used to estimate the noise PSD for computing noise LPCs. A whitening filter is also implemented with the noise LPCs to pre-whiten the noisy speech signal prior to estimating the speech LPCs. It is shown that the improved speech and noise LPCs enable the AKF to minimize the residual noise as well as distortion in the enhanced speech. Experimental results show that the enhanced speech produced by the proposed method exhibits higher quality and intelligibility than the benchmark methods in various noise conditions for a wide-range of SNR levels.
dc.relation.ispartofconferencename52nd IEEE International Symposium on Circuits and Systems (ISCAS 2020)
dc.relation.ispartofconferencetitle2020 IEEE International Symposium on Circuits and Systems (ISCAS)
dc.relation.ispartoflocationSevilla, Spain
dc.subject.fieldofresearchArtificial Intelligence and Image Processing
dc.subject.fieldofresearchCircuits and Systems
dc.titleDeep Learning with Augmented Kalman Filter for Single-Channel Speech Enhancement
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationRoy, SK; Nicolson, A; Paliwal, KK, Deep Learning with Augmented Kalman Filter for Single-Channel Speech Enhancement, 2020 IEEE International Symposium on Circuits and Systems (ISCAS), 2020
gro.hasfulltextNo Full Text
gro.griffith.authorRoy, Sujan Kumar K.
gro.griffith.authorPaliwal, Kuldip K.
gro.griffith.authorNicolson, Aaron M.

Files in this item


There are no files associated with 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