Advanced

Source Localization for Multiple Speech Sources Using Low Complexity Non-Parametric Source Separation and Clustering

Swartling, Mikael LU ; Sällberg, Benny and Grbic, Nedelko LU (2011) In Signal Processing 91(8). p.1781-1788
Abstract
This article presents a new method for localization of multiple concurrent speech sources that relies on simultaneous blind signal separation and direction of arrival (DOA) estimation, as well as a method to solve the intersection point selection problem that arises when locating multiple speech sources using multiple sensor arrays. The proposed method is based on a low complexity non-parametric blind signal separation method, making is suitable for real-time applications on embedded platforms. On top of reduced complexity in comparison to a previously presented method, the DOA estimation accuracy is also improved. Evaluation of the performance is done with both real recording and simulations, and a real-time prototype of the proposed... (More)
This article presents a new method for localization of multiple concurrent speech sources that relies on simultaneous blind signal separation and direction of arrival (DOA) estimation, as well as a method to solve the intersection point selection problem that arises when locating multiple speech sources using multiple sensor arrays. The proposed method is based on a low complexity non-parametric blind signal separation method, making is suitable for real-time applications on embedded platforms. On top of reduced complexity in comparison to a previously presented method, the DOA estimation accuracy is also improved. Evaluation of the performance is done with both real recording and simulations, and a real-time prototype of the proposed method has been implemented on a DSP platform to evaluate the computational and the memory complexities in a real application. (Less)
Please use this url to cite or link to this publication:
author
publishing date
type
Contribution to journal
publication status
published
subject
in
Signal Processing
volume
91
issue
8
pages
8 pages
publisher
Elsevier
external identifiers
  • Scopus:79955473942
ISSN
0165-1684
DOI
10.1016/j.sigpro.2011.02.002
language
English
LU publication?
no
id
656b2c5d-8579-4a84-a8c9-2e87b08da390
date added to LUP
2016-06-23 14:13:52
date last changed
2016-10-13 05:10:46
@misc{656b2c5d-8579-4a84-a8c9-2e87b08da390,
  abstract     = {This article presents a new method for localization of multiple concurrent speech sources that relies on simultaneous blind signal separation and direction of arrival (DOA) estimation, as well as a method to solve the intersection point selection problem that arises when locating multiple speech sources using multiple sensor arrays. The proposed method is based on a low complexity non-parametric blind signal separation method, making is suitable for real-time applications on embedded platforms. On top of reduced complexity in comparison to a previously presented method, the DOA estimation accuracy is also improved. Evaluation of the performance is done with both real recording and simulations, and a real-time prototype of the proposed method has been implemented on a DSP platform to evaluate the computational and the memory complexities in a real application.},
  author       = {Swartling, Mikael and Sällberg, Benny and Grbic, Nedelko},
  issn         = {0165-1684},
  language     = {eng},
  number       = {8},
  pages        = {1781--1788},
  publisher    = {ARRAY(0xa078cd8)},
  series       = {Signal Processing},
  title        = {Source Localization for Multiple Speech Sources Using Low Complexity Non-Parametric Source Separation and Clustering},
  url          = {http://dx.doi.org/10.1016/j.sigpro.2011.02.002},
  volume       = {91},
  year         = {2011},
}