Title :
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
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;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.674447
