Flow-Based Independent Vector Analysis for Blind Source Separation
Open Access
- 24 November 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 27 (10709908), 2173-2177
- https://doi.org/10.1109/lsp.2020.3039944
Abstract
This letter describes a time-varying extension of independent vector analysis (IVA) based on the normalizing flow (NF), called NF-IVA, for determined blind source separation of multichannel audio signals. As in IVA, NF-IVA estimates demixing matrices that transform mixture spectra to source spectra in the complex-valued spatial domain such that the likelihood of those matrices for the mixture spectra is maximized under some non-Gaussian source model. While IVA performs a time-invariant bijective linear transformation, NF-IVA performs a series of time-varying bijective linear transformations (flow blocks) adaptively predicted by neural networks. To regularize such transformations, we introduce a soft volume-preserving (VP) constraint. Given mixture spectra, the parameters of NF-IVA are optimized by gradient descent with backpropagation in an unsupervised manner. Experimental results show that NF-IVA successfully performs speech separation in reverberant environments with different numbers of speakers and microphones and that NF-IVA with the VP constraint outperforms NF-IVA without it, standard IVA with iterative projection, and improved IVA with gradient descent.Keywords
Funding Information
- JSPS KAKENHI (JP19H04137, JP20H01159, JP20K19833)
- NII CRIS Collaborative Research
- NII CRIS and LINE Corporation
This publication has 30 references indexed in Scilit:
- The signal separation evaluation campaign (2007–2010): Achievements and remaining challengesSignal Processing, 2012
- Density estimation by dual ascent of the log-likelihoodCommunications in Mathematical Sciences, 2010
- Fast fixed-point independent vector analysis algorithms for convolutive blind source separationSignal Processing, 2007
- Solution of Permutation Problem in Frequency Domain ICA, Using Multivariate Probability Density FunctionsLecture Notes in Computer Science, 2006
- An approach to blind source separation based on temporal structure of speech signalsNeurocomputing, 2001
- Fast and robust fixed-point algorithms for independent component analysisIEEE Transactions on Neural Networks, 1999
- Independent component analysis, A new concept?Signal Processing, 1994
- Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architectureSignal Processing, 1991
- Short term spectral analysis, synthesis, and modification by discrete Fourier transformIEEE Transactions on Acoustics, Speech, and Signal Processing, 1977
- An Iterative Algorithm for Computing the Best Estimate of an Orthogonal MatrixSIAM Journal on Numerical Analysis, 1971