Algorithmic compositions based on discovered musical patterns

Shan, Man-Kwan; Chiu, Shih-Chuan

doi:10.1007/s11042-009-0303-y

Cited by 19 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to learn the patterns that will be used to compose new melodies, it is necessary to analyse the available samples to identify and extract the required elements for the composition, namely: rhythmic patterns, pitch contours, harmonic progressions and tempo information (needed for the proper analysis of the data). Similar developments are proposed in [22].…”

Section: Pattern Analysersupporting

confidence: 54%

Automatic melody composition based on a probabilistic model of music style and harmonic rules

Roig

Tardón

Barbancho

et al. 2014

Knowledge-Based Systems

View full text Add to dashboard Cite

Section: Pattern Analysersupporting

confidence: 54%

Automatic melody composition based on a probabilistic model of music style and harmonic rules

Roig

Tardón

Barbancho

et al. 2014

Knowledge-Based Systems

View full text Add to dashboard Cite

“…Cope also argued that the recombination of existing excerpts is a basic technique frequently used by composers. More recently, Shan and Chiu [2010] used machine learning techniques to analyze existing music samples and proposed a top-down algorithmic composition system that generates music pieces similar to the given samples. Combining music clips in the symbolic domain causes no obvious audible artifacts in the auditory aspect.…”

Section: Symbolic Music Combinationmentioning

confidence: 99%

Audio Musical Dice Game

Lin

Liu

Jang

et al. 2015

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

This article proposes a framework for creating user-preference-aware music medleys from users' music collections. We treat the medley generation process as an audio version of a musical dice game. Once the user's collection has been analyzed, the system is able to generate various pleasing medleys. This flexibility allows users to create medleys according to the specified conditions, such as the medley structure or the must-use clips. Even users without musical knowledge can compose medley songs from their favorite tracks. The effectiveness of the system has been evaluated through both objective and subjective experiments on individual components in the system. . 2015. Audio musical dice game: A userpreference-aware medley generating system. ACM Trans. Multimedia Comput. Commun.

show abstract

“…An intelligent system aimed at creating new musical pieces is reported in [26], where feature extraction helps discover musical patterns of popular songs, and then profit from those patterns to create novel compositions. Human evaluation acts as feedback to adjust genetic algorithms that create pieces of music [27].…”

Section: Emotions As a Parameter To Recommend Musicmentioning

confidence: 99%