Title :
A neural network based dynamic reconstruction filter for digital audio signals
Author :
Najafi, Hossein L. ; Moses, D.W. ; Hustig, C.H. ; Kinne, J.
Author_Institution :
Dept. of Comput. Sci., Univ. of Wisconsin, River Falls, WI, USA
Abstract :
The goal of any digital audio system is to sample and reconstruct an analog audio signal, without noticeable changes to the original signal. Currently, two major types of reconstruction filters, brickwall and monotonic filters, are used to smooth a sampled analog audio signal during its reconstruction. Brickwall filters work best on reconstruction of smooth signals and the monotonic filters are best for reconstruction of transient signals. Since audio is composed of mixed transient and smooth signals, both of these filters will introduce undesirable artifacts to the signal during its reconstruction. The paper presents a new neural network based dynamic reconstruction filter that can change its behavior to best match the type of signal that is being filtered
Keywords :
audio signals; filters; neural nets; signal reconstruction; signal sampling; analog audio signal reconstruction; analog audio signal sampling; artifacts; brickwall filters; digital audio signals; mixed transient/smooth signals; monotonic filters; neural network based dynamic reconstruction filter; sampled analog audio signal smoothing; transient signal reconstruction; Audio systems; Band pass filters; Digital filters; Frequency; Image reconstruction; Matched filters; Neural networks; Passband; Rivers; Signal sampling;
Conference_Titel :
Knowledge-Based Intelligent Electronic Systems, 1997. KES '97. Proceedings., 1997 First International Conference on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-3755-7
DOI :
10.1109/KES.1997.619448
