Permutation inconsistency in blind speech separation: investigation and solutions
Authors:
- D.R. MorganDMD.R. Morgan
- 20 December 2004
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Speech and Audio Processing
- Vol. 13 (1) , 1-13
Abstract
Acoustic reverberation severely limits the performance of multiple microphone blind speech separation (BSS) methods. We show that the limited performance is due to random permutations of the unmixing filters over frequency. This problem, which we refer to as permutation inconsistency, becomes worse as the length of the room impulse response increases. We explore interesting connections between BSS and ideal beamforming, which leads us to propose a permutation alignment scheme based on microphone array directivity patterns. Given that the permutations are properly aligned, we show that the blind speech separation method outperforms the nonblind beamformer in a highly reverberant environment. Furthermore, we discover the tradeoff where permutations can be aligned by affording a loss in spectral resolution of the unmixing filters. We then propose a multistage algorithm, which aligns the unmixing filter permutations without sacrificing the spectral resolution. For our study, we perform experiments in both real and simulated environments and compare the results to the ideal performance benchmarks that we derive using prior knowledge of the mixing filters.Keywords
This publication has 18 references indexed in Scilit:
- Feasibility of source separation in frequency domain2002
- An approach to blind source separation based on temporal structure of speech signalsNeurocomputing, 2001
- Evaluation of blind signal separation method using directivity pattern under reverberant conditions2000
- Convolutive blind separation of non-stationary sourcesIEEE Transactions on Speech and Audio Processing, 2000
- Blind signal separation: statistical principlesProceedings of the IEEE, 1998
- A parametric error analysis of the backward integration method for reverberation time estimationThe Journal of the Acoustical Society of America, 1997
- Blind separation of convolutive mixtures and an application in automatic speech recognition in a noisy environmentIEEE Transactions on Signal Processing, 1997
- Multi-channel signal separation by decorrelationIEEE Transactions on Speech and Audio Processing, 1993
- Indeterminacy and identifiability of blind identificationIEEE Transactions on Circuits and Systems, 1991
- Image method for efficiently simulating small-room acousticsThe Journal of the Acoustical Society of America, 1979