Paper Info
Title
Online inter-frame correlation estimation methods for speech enhancement in frequency subbands
Abstract
In this paper, we propose solutions for the online adaptation of optimal FIR filters for speech enhancement in DFT subbands. An important ingredient to such filters is the estimation of the inter-frame correlation of the clean speech signal. While this correlation was assumed to be perfectly known in former studies, we discuss two online estimation approaches based on a constant noise inter-frame correlation and on the use of a binary mask. We show that a filtering of subband signals based on these estimated quantities outperforms a conventional, instantaneous spectral weighting, such as the frequency-domain Wiener filter at least for high SNR conditions.
Year
DOI
Venue
2013
10.1109/ICASSP.2013.6639117
Acoustics, Speech and Signal Processing
Keywords
Field
DocType
FIR filters,correlation methods,discrete Fourier transforms,speech enhancement,DFT subbands,binary mask,clean speech signal,constant noise interframe correlation,discrete Fourier transform,frequency subbands,frequency-domain Wiener filter,high SNR conditions,instantaneous spectral weighting,online interframe correlation estimation methods,optimal FIR filters,speech enhancement,subband signals,MVDR,Noise reduction,Wiener filter,filter-bank system,subband filtering
Speech enhancement,Wiener filter,Weighting,Pattern recognition,Computer science,Filter (signal processing),Inter frame correlation,Correlation,Artificial intelligence,Finite impulse response,Binary number
Conference
ISSN
Citations 
PageRank 
1520-6149
4
0.49
References 
Authors
7
2
Name
Order
Citations
PageRank
Schasse, A.1171.97
Rainer Martin2102991.14