SPSA for noisy non-stationary blind source separation

G.H. Morison, T.S. Durrani

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

In this paper a novel application of the simultaneous perturbation stochastic approximation algorithm (SPSA) to the noisy non-stationary blind source separation problem is presented and described. The proposed approach demonstrates the algorithm with a second order cost function suitable for applications to non-stationary data. Some extensions to the algorithm that are currently being investigated are also described in the paper, and the algorithm performance is demonstrated via simulation.

Conference

Conference2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
CountryHong Kong
CityHong Kong
Period6/04/0310/04/03

Fingerprint

Blind source separation
Approximation algorithms
Cost functions

Keywords

  • SPSA
  • non-stationary
  • blind source separation
  • noisy
  • approximation algorithms
  • vectors
  • stochastic processes
  • source separation
  • signal processing
  • sensor arrays
  • management training
  • equations
  • cost function
  • blind source separation

Cite this

Morison, G. H., & Durrani, T. S. (2003). SPSA for noisy non-stationary blind source separation. 285-288. Paper presented at 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). , Hong Kong, Hong Kong. https://doi.org/10.1109/ICASSP.2003.1199925
Morison, G.H. ; Durrani, T.S. / SPSA for noisy non-stationary blind source separation. Paper presented at 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). , Hong Kong, Hong Kong.4 p.
@conference{fbf00a59bcf9419bbfc68dcb3eb940ee,
title = "SPSA for noisy non-stationary blind source separation",
abstract = "In this paper a novel application of the simultaneous perturbation stochastic approximation algorithm (SPSA) to the noisy non-stationary blind source separation problem is presented and described. The proposed approach demonstrates the algorithm with a second order cost function suitable for applications to non-stationary data. Some extensions to the algorithm that are currently being investigated are also described in the paper, and the algorithm performance is demonstrated via simulation.",
keywords = "SPSA, non-stationary, blind source separation, noisy, approximation algorithms , vectors , stochastic processes , source separation , signal processing , sensor arrays , management training, equations, cost function , blind source separation",
author = "G.H. Morison and T.S. Durrani",
year = "2003",
month = "4",
doi = "10.1109/ICASSP.2003.1199925",
language = "English",
pages = "285--288",
note = "2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). ; Conference date: 06-04-2003 Through 10-04-2003",

}

Morison, GH & Durrani, TS 2003, 'SPSA for noisy non-stationary blind source separation' Paper presented at 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). , Hong Kong, Hong Kong, 6/04/03 - 10/04/03, pp. 285-288. https://doi.org/10.1109/ICASSP.2003.1199925

SPSA for noisy non-stationary blind source separation. / Morison, G.H.; Durrani, T.S.

2003. 285-288 Paper presented at 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). , Hong Kong, Hong Kong.

Research output: Contribution to conferencePaper

TY - CONF

T1 - SPSA for noisy non-stationary blind source separation

AU - Morison, G.H.

AU - Durrani, T.S.

PY - 2003/4

Y1 - 2003/4

N2 - In this paper a novel application of the simultaneous perturbation stochastic approximation algorithm (SPSA) to the noisy non-stationary blind source separation problem is presented and described. The proposed approach demonstrates the algorithm with a second order cost function suitable for applications to non-stationary data. Some extensions to the algorithm that are currently being investigated are also described in the paper, and the algorithm performance is demonstrated via simulation.

AB - In this paper a novel application of the simultaneous perturbation stochastic approximation algorithm (SPSA) to the noisy non-stationary blind source separation problem is presented and described. The proposed approach demonstrates the algorithm with a second order cost function suitable for applications to non-stationary data. Some extensions to the algorithm that are currently being investigated are also described in the paper, and the algorithm performance is demonstrated via simulation.

KW - SPSA

KW - non-stationary

KW - blind source separation

KW - noisy

KW - approximation algorithms

KW - vectors

KW - stochastic processes

KW - source separation

KW - signal processing

KW - sensor arrays

KW - management training

KW - equations

KW - cost function

KW - blind source separation

U2 - 10.1109/ICASSP.2003.1199925

DO - 10.1109/ICASSP.2003.1199925

M3 - Paper

SP - 285

EP - 288

ER -

Morison GH, Durrani TS. SPSA for noisy non-stationary blind source separation. 2003. Paper presented at 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). , Hong Kong, Hong Kong. https://doi.org/10.1109/ICASSP.2003.1199925