Joint estimation of DOA and speech based on EM beamforming

Author

Kim, Lae-Hoon ; Hasegawa-Johnson, Mark ; Potamianos, Gerasimos ; Libal, Vit

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Illinois, Urbana, IL, USA

fYear

2010

fDate

14-19 March 2010

Firstpage

121

Lastpage

124

Abstract

In this paper, we propose a multi-microphone joint optimal estimation of the direction of arrival (DOA) and the source speech signal through newly introduced EM beamforming. This produces a posterior PDF for the DOA, based only on the reliable speech spectrum. By maximizing over the posterior PDF of the DOA, we achieve maximum a posteriori DOA estimation. After convergence, the estimated source spectrum through weighted sum in the Bayesian sense is a maximum likelihood estimate (MLE). This is a sufficient statistic for minimum mean square error (MMSE) optimal estimation using a subsequent single channel MMSE filter.

Keywords

array signal processing; direction-of-arrival estimation; least mean squares methods; maximum likelihood estimation; speech processing; Bayesian sense; DOA estimation; EM beamforming; MLE; PDF; direction of arrival; maximum likelihood estimate; minimum mean square error; multi-microphone joint optimal estimation; single channel MMSE filter; source speech signal; speech estimation; Array signal processing; Bayesian methods; Convergence; Direction of arrival estimation; Filters; Frequency estimation; Maximum likelihood estimation; Mean square error methods; Microphones; Speech enhancement; Bayesian beamforming; EM beamforming; direction of arrival; multi-microphone; optimal speech enhancement;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on

Conference_Location

Dallas, TX

ISSN

1520-6149

Print_ISBN

978-1-4244-4295-9

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2010.5496144

Filename

5496144