Removal of noise from speech using the dual EKF algorithm

Author

Wan, Eric A. ; Nelson, Alex T.

Author_Institution

Dept. of Electr. & Comput. Eng., Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA

Volume

1

fYear

1998

fDate

12-15 May 1998

Firstpage

381

Abstract

Noise reduction for speech signals has applications ranging from speech enhancement for cellular communications, to front ends for speech recognition systems. A neural network based time-domain method called dual extended Kalman filtering (dual EKF) is presented for removing nonstationary and colored noise from speech. This paper describes the algorithm and provides a set of experimental results

Keywords

Kalman filters; cellular radio; feedforward neural nets; filtering theory; nonlinear filters; recursive estimation; speech enhancement; speech recognition; state-space methods; time-domain analysis; white noise; cellular communications; colored noise; dual EKF algorithm; dual extended Kalman filtering; experimental results; feedforward networks; front ends; neural network based time-domain method; noise reduction; noise removal; nonstationary noise; recursive estimation; speech enhancement; speech recognition systems; speech signals; state space methods; white noise; Additive noise; Filtering; Kalman filters; Neural networks; Noise reduction; Signal processing; Speech enhancement; Speech processing; State estimation; Time domain analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Seattle, WA

ISSN

1520-6149

Print_ISBN

0-7803-4428-6

Type

conf

DOI

10.1109/ICASSP.1998.674447

Filename

674447