On optimal and universal nonlinearities for blind signal separation

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 5, Issue , 2001, Pages 2777-2780

  Mathis, Heinz ^a   Douglas, Scott C ^b  

^a ETH ZURICH   (Switzerland)

^b Southern Methodist University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE ALGORITHMS; GRADIENT METHODS; MATHEMATICAL MODELS; MATRIX ALGEBRA; MAXIMUM LIKELIHOOD ESTIMATION; POLYNOMIALS; PROBABILITY DISTRIBUTIONS; RANDOM PROCESSES; VECTORS;

BLIND SIGNAL SEPARATION; THRESHOLD NONLINEARITY;

BLIND SOURCE SEPARATION;

EID: 0034853882     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940222     Document Type: Article

References (7)

1. Infomax and maximum likelihood for source separation
2. Stability analysis of adaptive blind source separation
3. Transpose properties in the stability and performance of the classic adaptive algorithms for blind source separation and deconvolution
4. On the stability of source separation algorithms
5. Self-stabilized gradient algorithms for blind source separation with orthogonality constraints
6. A simple threshold nonlinearity for blind signal separation