AES E-Library

Learning Algorithms for Audio Signal Enhancement, Part 1: Neural Network Implementation for the Removal of Impulse Distortions

Learning algorithms were implemented for the elimination of impulse distortions found in old records and in transmitted audio signals. Neural network simulations were tested with regard to the detection of scratches and clicks. Some special algorithms for the interpolation of distorted signal fragments were studied. Applied methods, results of musical signal processing, and conclusions are presented.

Author: Czyzewski, Andrzej
Affiliation: Technical University of Gdansk, Sound Engineering Department, Gdansk, Poland
JAES Volume 45 Issue 10 pp. 815-831; October 1997 Import into BibTeX

Click to purchase paper or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $20 for non-members, $5 for AES members and is free for E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD aes5)   /jrnl8997/1997/8694.pdf

Start a discussion about this paper!