Acoustic echo cancellation for hands-free telephony using neural networks

Author

Birkett, A.N. ; Goubran, R.A.

Author_Institution

Dept. of Syst. & Comput. Eng., Carleton Univ., Ottawa, Ont., Canada

fYear

1994

fDate

6-8 Sep 1994

Firstpage

249

Lastpage

258

Abstract

One of the limitations of linear adaptive echo cancellers in hands-free environments is their inability to effectively cancel nonlinearities which are generated mainly in the loudspeaker during large signal peaks. The soft-clipping effect encountered when large signals are applied to the loudspeaker is modelled in a neural network using a piecewise linear/sigmoid activation function. A three-layer fully adaptive feedforward network is used to model the room/speakerphone transfer function using the special activation function. This network structure improves the ERLE performance by 10 dB at low to medium loudspeaker volumes compared to a NLMS echo canceller

Keywords

acoustic signal processing; echo suppression; feedforward neural nets; telecommunication computing; telephone sets; telephony; acoustic echo cancellation; hands-free telephony; linear adaptive echo cancellers; neural networks; piecewise linear/sigmoid activation function; room/speakerphone transfer function; soft-clipping effect; three-layer adaptive feedforward network; Adaptive filters; Adaptive systems; Coils; Convergence; Echo cancellers; Loudspeakers; Magnetic levitation; Neural networks; Telephony; Transfer functions;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop

Conference_Location

Ermioni

Print_ISBN

0-7803-2026-3

Type

conf

DOI

10.1109/NNSP.1994.366042

Filename

366042