Change search
ReferencesLink to record
Permanent link

Direct link
Speech enhancement using intra- frame dependency in DCT domain
Indian Institute of Science.
Indian Institute of Science.ORCID iD: 0000-0003-2638-6047
Indian Institute of Science.
2008 (English)Conference paper (Refereed)
Abstract [en]

In this paper, we present a new speech enhancement approach, that is based on exploiting the intra-frame dependency of discrete cosine transform (DCT) domain coefficients. It can be noted that the existing enhancement techniques treat the transformdomain coefficients independently. Instead of this traditional approach of independently processing the scalars, we split the DCT domain noisy speech vector into sub-vectors and each sub-vector is enhanced independently. Through this sub-vector based approach, the higher dimensional enhancement advantage, viz. non-linear dependency, is exploited. In the developed method, each clean speech sub-vector is modeled using a Gaussian mixture (GM) density. We show that the proposed Gaussian mixture model (GMM) based DCT domain method, using sub-vector processing approach, provides better performance than the conventional approach of enhancing the transform domain scalar components independently. Performance improvement over the recently proposed GMM based time domain approach is also shown.

Place, publisher, year, edition, pages
Keyword [en]
Speech enhancement, estimation
National Category
Signal Processing
Research subject
URN: urn:nbn:se:kth:diva-46572OAI: diva2:453895
16th European Signal Processing Conference (EUSIPCO 2008), Lausanne, Switzerland, August 25-29, 2008
QC 20111107Available from: 2011-11-03 Created: 2011-11-03 Last updated: 2012-01-13Bibliographically approved

Open Access in DiVA

No full text

Other links

Search in DiVA

By author/editor
Chatterjee, Saikat
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 28 hits
ReferencesLink to record
Permanent link

Direct link