Paper Info
Title
Spectro-Temporal Filtering for Multichannel Speech Enhancement in Short-Time Fourier Transform Domain
Abstract
In this letter, we propose a spectro-temporal filtering algorithm for multichannel speech enhancement in the short-time Fourier transform (STFT) domain. Compared with the traditional multiplicative filtering technique, the proposed method takes account of interdependencies between components in adjacent frames and frequency bins. For spectro-temporal filtering, speech and noise power spectral density (PSD) matrices are estimated based on an extended formulation utilizing temporal and spectral correlations, and the parametric noise reduction filter based on these PSD matrices is applied to the input microphone array signal. Moreover, multichannel speech presence probabilities are also estimated within a unified framework. A number of experimental results show that the proposed spectro-temporal filtering method improves the performance of multichannel speech enhancement.
Year
DOI
Venue
2014
10.1109/LSP.2014.2302897
IEEE Signal Process. Lett.
Keywords
Field
DocType
fourier transforms,multichannel speech presence probability,signal denoising,spectral correlation,adjacent frame,spectro-temporal filtering,frequency bins,parametric noise reduction filter,speech power spectral density matrix,parameterized non-causal multichannel wiener filter,temporal correlation,noise power spectral density matrix,short time fourier transform domain,filtering theory,multichannel speech enhancement,speech enhancement,microphone array,noise reduction,speech,noise,correlation
Noise reduction,Speech enhancement,Noise power,Pattern recognition,Computer science,Filter (signal processing),Short-time Fourier transform,Fourier transform,Microphone array,Spectral density,Artificial intelligence
Journal
Volume
Issue
ISSN
21
3
1070-9908
Citations 
PageRank 
References 
5
0.43
7
Authors
3
Name
Order
Citations
PageRank
Yu Gwang Jin1114.10
Jong Won Shin221521.85
Nam Soo Kim327529.16