Subbands audio signal recovering using neural nonlinear prediction

Author

Cocchi, Gianandrea ; Uncini, Aurelio

Author_Institution

Dipt. INFOCOM, Rome Univ., Italy

Volume

2

fYear

2001

fDate

2001

Firstpage

1289

Abstract

Audio signal recovery is a common problem in the digital audio restoration field, because of corrupted samples that must be replaced. In this paper a subband architecture is presented for audio signal recovery, using neural nonlinear prediction based on adaptive spline neural networks. The experimental results show the mean square reconstruction error, and maximum error obtained with increasing gap length, from 200 to 5000 samples. The method gives good results allowing the reconstruction of over 100 ms of signal with low audible effects in overall quality

Keywords

adaptive signal processing; audio signal processing; channel bank filters; mean square error methods; neural nets; prediction theory; signal restoration; adaptive spline neural networks; audible quality effects; digital audio restoration field; gap length; maximum error; mean square reconstruction error; neural nonlinear prediction; subbands architecture; subbands audio signal recovery; Acoustic noise; Background noise; Filter bank; Finite impulse response filter; Magnetic noise; Multi-layer neural network; Neural networks; Neurons; Noise reduction; Signal restoration;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01). 2001 IEEE International Conference on

Conference_Location

Salt Lake City, UT

ISSN

1520-6149

Print_ISBN

0-7803-7041-4

Type

conf

DOI

10.1109/ICASSP.2001.941161

Filename

941161