Joint Dereverberation and Separation With Iterative Source Steering
Open Access
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 216-220
Abstract
We propose a new algorithm for joint dereverberation and blind source separation (DR-BSS). Our work builds upon the IRLMA-T framework that applies a unified filter combining dereverberation and separation. One drawback of this framework is that it requires several matrix inversions, an operation inherently costly and with potential stability issues. We leverage the recently introduced iterative source steering (ISS) updates to propose two algorithms mitigating this issue. Albeit derived from first principles, the first algorithm turns out to be a natural combination of weighted prediction error (WPE) dereverberation and ISS-based BSS, applied alternatingly. In this case, we manage to reduce the number of matrix inversion to only one per iteration and source. The second algorithm updates the ILRMA-T matrix using only sequential ISS updates requiring no matrix inversion at all. Its implementation is straightforward and memory efficient. Numerical experiments demonstrate that both methods achieve the same final performance as ILRMA-T in terms of several relevant objective metrics. In the important case of two sources, the number of iterations required is also similar.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- The third ‘CHiME’ speech separation and recognition challenge: Analysis and outcomesComputer Speech & Language, 2017
- Optimized Speech Dereverberation From Probabilistic Perspective for Time Varying Acoustic Transfer FunctionIEEE Transactions on Audio, Speech, and Language Processing, 2013
- Stable and fast update rules for independent vector analysis based on auxiliary function technique2011
- Speech Dereverberation Based on Variance-Normalized Delayed Linear PredictionIEEE Transactions on Audio, Speech, and Language Processing, 2010
- Blind Separation and Dereverberation of Speech Mixtures by Joint OptimizationIEEE Transactions on Audio, Speech, and Language Processing, 2010
- Speech Dereverberation2010
- Blind Speech Separation2007
- Blind Source Separation Exploiting Higher-Order Frequency DependenciesIEEE Transactions on Audio, Speech, and Language Processing, 2006
- An approach to blind source separation based on temporal structure of speech signalsNeurocomputing, 2001
- Independent component analysis, A new concept?Signal Processing, 1994