Microphone array speech enhancement by Bayesian estimation of spectral amplitude and phase

Author

Balan, Radu ; Rosca, Justinian

Author_Institution

Multimedia & Video Technol. Dept., Siemens Corporate Res., Princeton, NJ, USA

fYear

2002

fDate

4-6 Aug. 2002

Firstpage

209

Lastpage

213

Abstract

Microphone arrays provide new opportunities for noise reduction and speech enhancement. This paper presents a novel decomposition of the estimation problems for short-time spectral amplitude (STSA), log STSA, and phase in the Bayesian estimation framework. The decomposition is based on the notion of sufficient statistics for the microphone array case. It nicely generalizes the wellknown single-channel Ephraim-Malah estimators (1984, 1985) to the microphone array case. We also compare noise reduction obtained in the single channel with the two- and four-channel cases on real data.

Keywords

Bayes methods; acoustic transducer arrays; amplitude estimation; least mean squares methods; microphones; noise abatement; phase estimation; spectral analysis; speech enhancement; statistical analysis; Bayesian estimation; MMSE estimators; STFT estimator; STSA; estimation problems; log STSA; microphone arrays; noise reduction; phase estimation; short-time spectral amplitude; single-channel Ephraim-Malah estimators; spectral amplitude estimation; speech enhancement; sufficient statistics; Amplitude estimation; Array signal processing; Bayesian methods; Gaussian noise; MONOS devices; Microphone arrays; Noise reduction; Phase estimation; Phased arrays; Speech enhancement;

fLanguage

English

Publisher

ieee

Conference_Titel

Sensor Array and Multichannel Signal Processing Workshop Proceedings, 2002

Print_ISBN

0-7803-7551-3

Type

conf

DOI

10.1109/SAM.2002.1191030

Filename

1191030