Advanced

Direction of arrival estimation for multiple speakers using time-frequency orthogonal signal separation

Swartling, Mikael LU ; Grbic, Nedelko LU and Claesson, Ingvar LU (2006) IEEE International Conference on Acoustics, Speech, and Signal Processing, 2006 In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'06) 4. p.833-836
Abstract
This paper presents a new approach for multiple speaker DOA estimation using an array of microphones. The method relies on the fact that multiple independent speakers have a small overlap in the time-frequency domain, i.e. the individual signals are almost W-disjoint orthogonal. By introducing a time-frequency mask and by continuously tracking the set of time-frequency points corresponding to each individual speech signal, a single source DOA estimation algorithm is used to find the DOA for each separated signal. This approach does not limit the solution to cases where the number of sensors exceeds the number of sources. Real room recordings are used to evaluate the performance of the method where source movements are also included.
Please use this url to cite or link to this publication:
author
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'06)
volume
4
pages
4 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2006
external identifiers
  • Scopus:33947689599
ISBN
1-4244-0469-X
DOI
10.1109/ICASSP.2006.1661098
language
English
LU publication?
no
id
7c137e3e-2ee1-4ba6-9239-e2468852c129
date added to LUP
2016-06-23 16:16:06
date last changed
2016-10-13 05:10:50
@misc{7c137e3e-2ee1-4ba6-9239-e2468852c129,
  abstract     = {This paper presents a new approach for multiple speaker DOA estimation using an array of microphones. The method relies on the fact that multiple independent speakers have a small overlap in the time-frequency domain, i.e. the individual signals are almost W-disjoint orthogonal. By introducing a time-frequency mask and by continuously tracking the set of time-frequency points corresponding to each individual speech signal, a single source DOA estimation algorithm is used to find the DOA for each separated signal. This approach does not limit the solution to cases where the number of sensors exceeds the number of sources. Real room recordings are used to evaluate the performance of the method where source movements are also included.<br/>},
  author       = {Swartling, Mikael and Grbic, Nedelko and Claesson, Ingvar},
  isbn         = {1-4244-0469-X},
  language     = {eng},
  pages        = {833--836},
  publisher    = {ARRAY(0x91b5d20)},
  series       = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'06)},
  title        = {Direction of arrival estimation for multiple speakers using time-frequency orthogonal signal separation},
  url          = {http://dx.doi.org/10.1109/ICASSP.2006.1661098 },
  volume       = {4},
  year         = {2006},
}