File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Improved speech presence probability estimation based on wavelet denoising

TitleImproved speech presence probability estimation based on wavelet denoising
Authors
Issue Date2012
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000089
Citation
The 2012 IEEE International Symposium on Circuits and Systems (ISCAS), Seoul, South Korea, 20-23 May 2012. In IEEE International Symposium on Circuits and Systems Proceedings, 2012, p. 1018-1021 How to Cite?
AbstractA reliable estimator for speech presence probability (SPP) can significantly improve the performance of many speech enhancement algorithms. Previous work showed that a good SPP estimator can be obtained by using a smooth a-posteriori signal to noise ratio (SNR) function, which can be achieved by reducing the noise variance when estimating the speech power spectrum. In this paper, a wavelet based denoising algorithm is proposed for such purpose. We first apply the wavelet transform to the periodogram of a noisy speech signal to generate an oracle for indicating the locations of the noise floor in the periodogram. We then make use of that oracle to selectively remove the wavelet coefficients of the noise floor in the log multitaper spectrum (MTS) of the noisy speech. The remaining wavelet coefficients are then used to reconstruct a denoised MTS and in turn generate a smooth a-posteriori SNR function. Simulation results show that the new SPP estimator outperforms the traditional approaches and enables a significantly improvement in the quality and intelligibility of the enhanced speeches. © 2012 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/202308
ISBN
ISSN

 

DC FieldValueLanguage
dc.contributor.authorLun, DPK-
dc.contributor.authorShen, TW-
dc.contributor.authorHsung, TC-
dc.contributor.authorHo, DKC-
dc.date.accessioned2014-09-11T03:47:06Z-
dc.date.available2014-09-11T03:47:06Z-
dc.date.issued2012-
dc.identifier.citationThe 2012 IEEE International Symposium on Circuits and Systems (ISCAS), Seoul, South Korea, 20-23 May 2012. In IEEE International Symposium on Circuits and Systems Proceedings, 2012, p. 1018-1021-
dc.identifier.isbn978-1-4673-0219-7-
dc.identifier.issn0271-4302-
dc.identifier.urihttp://hdl.handle.net/10722/202308-
dc.description.abstractA reliable estimator for speech presence probability (SPP) can significantly improve the performance of many speech enhancement algorithms. Previous work showed that a good SPP estimator can be obtained by using a smooth a-posteriori signal to noise ratio (SNR) function, which can be achieved by reducing the noise variance when estimating the speech power spectrum. In this paper, a wavelet based denoising algorithm is proposed for such purpose. We first apply the wavelet transform to the periodogram of a noisy speech signal to generate an oracle for indicating the locations of the noise floor in the periodogram. We then make use of that oracle to selectively remove the wavelet coefficients of the noise floor in the log multitaper spectrum (MTS) of the noisy speech. The remaining wavelet coefficients are then used to reconstruct a denoised MTS and in turn generate a smooth a-posteriori SNR function. Simulation results show that the new SPP estimator outperforms the traditional approaches and enables a significantly improvement in the quality and intelligibility of the enhanced speeches. © 2012 IEEE.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000089-
dc.relation.ispartofIEEE International Symposium on Circuits and Systems Proceedings-
dc.rightsIEEE International Symposium on Circuits and Systems Proceedings. Copyright © IEEE.-
dc.rights©2012 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.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleImproved speech presence probability estimation based on wavelet denoisingen_US
dc.typeConference_Paperen_US
dc.identifier.emailHsung, TC: tchsung@hku.hk-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ISCAS.2012.6271400-
dc.identifier.scopuseid_2-s2.0-84866611127-
dc.identifier.hkuros238330-
dc.identifier.spage1018-
dc.identifier.epage1021-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 140911-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats