Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-L10.1 |
| Session: | Multichannel Speech Enhancement |
| Time: | Friday, May 21, 13:00 - 13:20 |
| Presentation: |
Lecture |
| Topic: |
Speech Processing: Speech Enhancement |
| Title: |
OPTIMAL BLIND SEPARATION OF CONVOLUTIVE AUDIO MIXTURES WITHOUT TEMPORAL CONSTRAINTS |
| Authors: |
Kostas Kokkinakis; University of Liverpool | | |
| | Asoke K. Nandi; University of Liverpool | | |
| Abstract: |
This paper addresses the blind separation of convolutive and temporally correlated speech mixtures, through the use of a multichannel blind deconvolution (MBD) method. In the proposed method (NGA-LP) spatio-temporal separation is achieved by entropy maximization using the natural gradient algorithm (NGA), while a temporal prewhitening stage, based on linear prediction (LP), preserves the original spectral characteristics of each source contribution. It is further shown that a parameterized optimal nonlinearity derived from the generalized Gaussian density (GGD) model, increases the overall separation performance. Experiments with convolutive mixtures illustrate the merits of the proposed method. |
| |
| Back | |