A semi-blind approach to the separation of real world speech mixtures

Proceedings of the International Joint Conference on Neural Networks

Volumn 2, Issue , 2002, Pages 1293-1298

  Tordini, F ^a   Piazza, F ^a  

^a RSC Dept   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; BLIND SOURCE SEPARATION; COMPUTER SIMULATION; FAST FOURIER TRANSFORMS; FEATURE EXTRACTION; MATHEMATICAL MODELS; PROBABILITY DENSITY FUNCTION;

MULTICHANNEL BLIND DECONVOLUTION ALGORITHM; PITCH; SOFTWARE PACKAGE MATLAB;

SPEECH ANALYSIS;

EID: 0036079691     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. A new learning algorithm for blind signal separation
2. Geometrical structures of FIR manifold and their application to multichannel blind deconvolution
3. Enhancement of a speech signal embedded in noisy environment using two microphones
4. An information maximization approach to blind separation and blind deconvolution
5. Second order blind separation of temporally correlated sources
6. Equivariant adaptive source separation
7. Development of innovative techniques for blind separation of audio signals: Single band and multi-band solutions
8. Independent component analysis: A new concept
9. A computationally efficient multipitch analysis model
10. A bayesian approach to source separation
11. Multichannel blind deconvolution: FIR matrix algebra and separation of multipath mixtures
12. Maximum likelihood and covariant algorithms for independent component analysis
13. A semi-blind approach to the separation of convolutional vocal mixtures