Multichannel parametric speech enhancement

Author

Srinivasan, Sriram ; Aichner, Robert ; Kleijn, W. Bastiaan ; Kellermann, Walter

Author_Institution

Dept. of Signals, R. Inst. of Technol., Stockholm, Sweden

Volume

13

Issue

5

fYear

2006

fDate

5/1/2006 12:00:00 AM

Firstpage

304

Lastpage

307

Abstract

We present a parametric model-based multichannel approach for speech enhancement. By employing an autoregressive model for the speech signal and using a trained codebook of speech linear predictive coefficients, minimum mean square error estimation of the speech signal is performed. By explicitly accounting for steering errors in the signal model, robust estimates are obtained. Experiments show that the proposed method results in significant performance gains.

Keywords

linear predictive coding; mean square error methods; speech coding; speech enhancement; autoregressive model; linear predictive coefficient; minimum mean square error estimation; multichannel parametric speech enhancement; speech signal; trained codebook; Acoustic noise; Acoustic signal processing; Additive noise; Array signal processing; Mean square error methods; Microphones; Noise cancellation; Noise reduction; Sensor arrays; Speech enhancement; Acoustic noise; acoustic signal processing; array signal processing; autoregressive processes; speech enhancement; speech processing;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/LSP.2005.863819

Filename

1618703