Convolutive blind separation of non-stationary sources

By Lucas C. Parra, Clay D. Spence. IEEE Transactions on Speech and Audio Processing, 2000

828 citations recorded by the source corpus.

Subfields: Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ce8e1b7107a452e5e4f2d6374ed89b83a421ce34

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Signal Processing

Citations in the corpus

Time-domain blind audio source separation using advanced ICA methods (2007, methodology): “[9] Parra, L., and Spence, C.: “Convolutive Blind Separation of Non-Stationary Sources”, IEEE Trans. on Speech and Audio Processing, Vol. 8, No. 3, pp. 320-327, May 2000.”
Recipes for the linear analysis of EEG (2005, methodology): “…algorithms are based on simultaneous diagonalization of multiple (more than two) cross-moments such as JADE (Cardoso and Souloumiac, 1993, 1996), SOBI (Belouchrani et al., 1997), or multiple decorrelations (Parra and Spence, 2000; Parra and Sajda, 2003; Pham and Cardoso, 2001; Ziehe et al., 2004).”
Blind Source Separation and Independent Component Analysis: A Review (2005, methodology): “Therefore, multiple different equations for the covariance matrices such as (105) can be obtained for different choices of K to provide successful estimation of the independent components [119, 142].”
Independent Vector Analysis: An Extension of ICA to Multivariate Components (2006, methodology): “method that limits the filter length in the time domain [ 4 ], uses direction of arrival estimation [5], and uses inter-frequency correlation [6].”
The Matrix Cookbook (2006, methodology): “The Conjugate Complex Derivative has e.g been used by [11] when deriving a complex gradient.”
Time-Domain Blind Separation of Audio Sources on the Basis of a Complete ICA Decomposition of an Observation Space (2011, methodology): “The second algorithm is that of Parra from [6] with two lengths of FFT, respectively, 512 (Parra-1) and 128 (Parra-2); the other parameters had the default values.”
Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech (2001, methodology): “In the case of a noise canceller, we should use an FIR filter of length ; therefore, . iii) If we want to estimate the inverse system of a system with impulse response -taps long, we need an inverse system that is-taps long, where ; therefore, .”
A robust and precise method for solving the permutation problem of frequency-domain blind source separation (2004, neutral): “This has been realized by averaging separation matrices with adjacent frequencies [8], limiting the filter length in the time domain [8], [16], [17], [22], or considering the coherency of separation matrices at adjacent frequencies [14].”
Multichannel Eigenspace Beamforming in a Reverberant Noisy Environment With Multiple Interfering Speech Signals (2009, methodology): “Independent component analysis (ICA) algorithms [2], [3] are commonly applied for solving the BSS problem.”
Blind Source Separation and Independent Component Analysis : A Review (2004, methodology): “Therefore, multiple different equations for the covariance matrices such as (105) can be obtained for different choices of K to provide successful estimation of the independent components [119, 142].”