Document Type
Thesis
Date of Award
12-31-1991
Degree Name
Master of Science in Computer Science - (M.S.)
Department
Computer and Information Science
First Advisor
Bonnie Kathleen MacKellar
Abstract
In this paper we describe an intelligent system used to aid an audio recording producer in the selection of edit points in a musical sequence. It is possible to make meaningful recommendations concerning auditory input data without the ability to fully classify that data or interpret all outside goals. Perceptual modeling of the auditory input can allow sufficient reasoning ability for an intelligent system to be of use editing digital audio. To create a perceptual model, the information which can be extracted by the ear is embodied in several expert sections which communicate with a rule based decision maker via a blackboard. The envelope expert "listens" for the changes in amplitude. The spectrum expert examines spectral changes. The rhythm expert examines the distances between note crests. This paper is intended to describe the architecture and discuss its use in the creation of an intelligent editing system.
Recommended Citation
Goode, J. Mark, "Editing digital audio using a perceptual model" (1991). Theses. 2488.
https://digitalcommons.njit.edu/theses/2488
