Permutation inconsistency in blind speech separation: investigation and solutions

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on speech and audio processing 2005-01, Vol.13 (1), p.1-13
Main Authors: Ikram, M.Z., Morgan, D.R.
Format: Article
Language:English
Subjects:
Acoustics
Alignment
Applied sciences
Array signal processing
Beamforming
blind separation
Blinds
Exact sciences and technology
Filters
Frequency
Impulse response
Information, signal and communications theory
Microphone arrays
Microphones
permutation inconsistency
Permutations
Reverberation
room acoustics
Separation
Signal processing
Signal resolution
Source separation
Spectral resolution
Speech
Speech enhancement
Speech processing
speech signals
Studies
Telecommunications and information theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1063-6676
2329-9290
1558-2353
2329-9304
DOI:10.1109/TSA.2004.834441