Loading…

Automated musical transitions through rule-based synthesis using musical properties

•Smooth transitions are generated by using musical properties and a rule-base.•Few generic constructs create unique and musically accurate transitions.•On average, valid transitions are 87% unique.•Lack of genre-based rules provide flexibility in transition generation. We present a novel approach to...

Full description

Saved in:
Bibliographic Details
Published in:Entertainment computing 2018-12, Vol.28, p.59-67
Main Authors: Alihan Hadimlioglu, I., King, Scott A.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Smooth transitions are generated by using musical properties and a rule-base.•Few generic constructs create unique and musically accurate transitions.•On average, valid transitions are 87% unique.•Lack of genre-based rules provide flexibility in transition generation. We present a novel approach to automatically generating a smooth transition between two distinct compositions. Our system, Intelligent Transition Generator (ITG), generates a transition between two input compositions. ITG analyzes tablatures of the input compositions to extract relevant information, such as playing style, time signatures, chord similarities, and note durations to determine appropriate rules for creating the transition. The composition engine uses various algorithms to apply the rules based upon timing information. ITG typically generates 2–4 bars of random transitions that are smooth and musically harmonious. Our new method to automatically compose sections of music does not require guidance from a composer or a set of sample compositions and therefore, it provides an efficient approach, which could be used in the gaming industry for dynamic, event-based music. It also could be applied to other multimedia purposes such as generating transitions between tracks in media players.
ISSN:1875-9521
1875-953X
DOI:10.1016/j.entcom.2018.10.004