Change search
ReferencesLink to record
Permanent link

Direct link
Robust spectrum quantization for LP parameter enhancement
KTH, School of Electrical Engineering (EES), Signal Processing.
2015 (English)In: European Signal Processing Conference, European Signal Processing Conference, EUSIPCO , 2015, 1951-1954 p.Conference paper (Refereed)
Abstract [en]

In this paper, we investigate the denoising properties of robust vector quantization of the speech spectrum parameters in combination with a Kalman filter. The underlying assumption is that the high-energy speech regions can be used to reconstruct the low-energy regions destroyed by noise. This can be achieved through vector quantization with a properly weighted distortion measure. The performance of the proposed system, Kalman filtering with prior vector quantization, is compared with existing schemes for parameter estimation used in Kalman filtering. The results indicate significant improvement over the reference systems in both objective and subjective tests.

Place, publisher, year, edition, pages
European Signal Processing Conference, EUSIPCO , 2015. 1951-1954 p.
Keyword [en]
Kalman filters, Signal processing, De-noising, Kalman-filtering, Low energy regions, Reference systems, Speech spectra, Weighted distortion, Vector quantization
National Category
Signal Processing
URN: urn:nbn:se:kth:diva-194631ScopusID: 2-s2.0-84979900479OAI: diva2:1050420
12th European Signal Processing Conference, EUSIPCO 2004, 6 September 2004 through 10 September 2004

QC 20161129

Available from: 2016-11-29 Created: 2016-10-31 Last updated: 2016-11-29Bibliographically approved

Open Access in DiVA

No full text


Search in DiVA

By author/editor
Grancharov, VolodyaKleijn, W. Bastian
By organisation
Signal Processing
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar

Total: 5 hits
ReferencesLink to record
Permanent link

Direct link