Blind vector deconvolution: convolutive mixture models in short-time fourier transform domain

Authors:
Atsuo Hiroe
Affiliations:
Intelligent Systems Research Laboratory, Information Technologies Laboratories, Sony Corporation, Tokyo, Japan
Venue:
ICA'07 Proceedings of the 7th international conference on Independent component analysis and signal separation
Year:
2007

Citing 5
Cited 2

Natural gradient works efficiently in learning

Neural Computation
The Modulation Spectrogram: In Pursuit of an Invariant Representation of Speech

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 3 - Volume 3
Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 05
Independent vector analysis: an extension of ICA to multivariate components

ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
Solution of permutation problem in frequency domain ICA, using multivariate probability density functions

ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation

Combining superdirective beamforming and frequency-domain blind source separation for highly reverberant signals

EURASIP Journal on Audio, Speech, and Music Processing - Special issue on environmental sound synthesis, processing, and retrieval
Efficient blind dereverberation and echo cancellation based on independent component analysis for actual acoustic signals

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

For short-time Fourier Transform (STFT) domain ICA, dealing with reverberant sounds is a significant issue. It often invites a dilemma on STFT frame length: frames shorter than reverberation time (short frames) generate incomplete instantaneous mixtures, while too long frames may disturb the separation. To improve the separation of such reverberant sounds, the authors propose a new framework which accounts for STFT with short frames. In this framework, time domain convolutive mixtures are transformed to STFT domain convolutive mixtures. For separating the mixtures, an approach of applying another STFT is presented so as to treat them as instantaneous mixtures. The authors experimentally confirmed that this framework outperforms the conventional STFT domain ICA.