An analysis of the limitations of blind signal separation application with speech

Authors:
Daniel Smith;Jason Lukasiak;Ian S. Burnett
Affiliations:
Whisper Laboratories, School of Electrical, Computer and Telecommunications Engineering, University of Wollongong, NSW, Australia;Whisper Laboratories, School of Electrical, Computer and Telecommunications Engineering, University of Wollongong, NSW, Australia;Whisper Laboratories, School of Electrical, Computer and Telecommunications Engineering, University of Wollongong, NSW, Australia
Venue:
Signal Processing
Year:
2006

Citing 4
Cited 5

Topographic Independent Component Analysis

Neural Computation
CuBICA: independent component analysis by simultaneous third- and fourth-order cumulant diagonalization

IEEE Transactions on Signal Processing
Estimation of the information by an adaptive partitioning of the observation space

IEEE Transactions on Information Theory
Fast and robust fixed-point algorithms for independent component analysis

IEEE Transactions on Neural Networks

Validity of the Independence Assumption for the Separation of Instantaneous and Convolutive Mixtures of Speech and Music Sources

ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Determining mixing parameters from multispeaker data using speech-specific information

IEEE Transactions on Audio, Speech, and Language Processing
Blind audio source separation using sparsity based criterion for convolutive mixture case

ICA'07 Proceedings of the 7th international conference on Independent component analysis and signal separation
Noise speech wavelet analyzing in special time ranges

ICACT'10 Proceedings of the 12th international conference on Advanced communication technology
Noise wavelet evaluating near to zero by thresholding method analyzing

ICCC'11 Proceedings of the 2011 international conference on Computers and computing

Quantified Score

Hi-index	0.08

Visualization

Abstract

Blind Signal Separation (BSS) techniques are commonly employed in the separation of speech signals, using Independent Component Analysis (ICA) as the criterion for separation. This paper investigates the viability of employing ICA for real-time speech separation (where short frame sizes are the norm). The relationship between the statistics of speech and the assumption of statistical independence (at the core of ICA) is examined over a range of frame sizes. The investigation confirms that statistical independence is not a valid assumption for speech when divided into the short frames appropriate to real-time separation. This is primarily due to the quasi-stationary nature of speech over the temporal short term. We conclude that employing ICA for real-time speech separation will always result in limited performance due to a fundamental failure to meet the strict assumptions of ICA.