Convolutive blind separation of speech mixtures using the natural gradient

Authors:
Scott C. Douglas;Xiaoan Sun
Affiliations:
Department of Electrical Engineering, Southern Methodist University, P.O. Box 750338, Dallas, TX;Department of Electrical Engineering, Southern Methodist University, P.O. Box 750338, Dallas, TX
Venue:
Speech Communication - Special issue on speech processing for hearing aids
Year:
2003

Citing 6
Cited 13

Natural gradient works efficiently in learning

Neural Computation
On-line Convolutive Blind Source Separation of Non-Stationary Signals

Journal of VLSI Signal Processing Systems
Space-Time Processing for Wireless Communications

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
Blind Separation of Multiple Speakers in a Multipath Environment

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
Nonholonomic Orthogonal Learning Algorithms for Blind Source Separation

Neural Computation
Signal separation by symmetric adaptive decorrelation: stability,convergence, and uniqueness

IEEE Transactions on Signal Processing

Objective quality evaluation in blind source separation for speech recognition in a real room

Signal Processing
Time-domain convolutive blind source separation employing selective-tap adaptive algorithms

EURASIP Journal on Audio, Speech, and Music Processing
Frequency-domain blind source separation of many speech signals using near-field and far-field models

EURASIP Journal on Applied Signal Processing
Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms

Speech Communication
An adaptive stereo basis method for convolutive blind audio source separation

Neurocomputing
Empirical methods to determine the number of sources in single-channel musical signals

IEEE Transactions on Audio, Speech, and Language Processing
Speech dereverberation based on variance-normalized delayed linear prediction

IEEE Transactions on Audio, Speech, and Language Processing - Special issue on processing reverberant speech: methodologies and applications
Spatial efficiency of blind source separation based on decorrelation - subjective and objective assessment

Speech Communication
Combining superdirective beamforming and frequency-domain blind source separation for highly reverberant signals

EURASIP Journal on Audio, Speech, and Music Processing - Special issue on environmental sound synthesis, processing, and retrieval
A multistage approach to blind separation of convolutive speech mixtures

Speech Communication
Blind separation combined frequency invariant beamforming and ICA for far-field broadband acoustic signals

ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Correlated Postfiltering and Mutual Information in Pseudoanechoic Model Based Blind Source Separation

Journal of Signal Processing Systems
Modulation domain blind speech separation in noisy environments

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

Convolutive blind separation of speech, also known as the "cocktail party problem", is a challenging task for which few successful algorithms have been developed. In this paper, we explore two novel algorithms for separating mixtures of multiple speech signals as measured by multiple microphones in a room environment. Both algorithms are modifications of an existing approach for density-based multichannel blind deconvolution (MBD) using natural gradient adaptation. The first approach employs non-holonomic constraints on the multichannel separation system to effectively avoid the partial deconvolution of the extracted speech signals within the separation system's outputs. The second approach employs linear predictors within the coefficient updates and produces separated speech signals whose auto-correlation properties can be arbitrarily specified. Unlike MBD methods, the proposed techniques maintain the spectral content of the original speech signals in the extracted outputs. Performance comparisons of the proposed methods with existing techniques show their usefulness in separating real-world speech signal mixtures.