AI methods in algorithmic composition: a comprehensive survey
Reads0
Chats0
TLDR
Algorithmic composition is the partial or total automation of the process of music composition by using computers as discussed by the authors, which can be classified into three main categories: partial or complete automation, automation, and complete automation.Abstract:
Algorithmic composition is the partial or total automation of the process of music composition by using computers. Since the 1950s, different computational techniques related to Artificial Intelligence have been used for algorithmic composition, including grammatical representations, probabilistic methods, neural networks, symbolic rule-based systems, constraint programming and evolutionary algorithms. This survey aims to be a comprehensive account of research on algorithmic composition, presenting a thorough view of the field for researchers in Artificial Intelligence.read more
Citations
More filters
Journal Article
Deep Learning Techniques for Music Generation - A Survey
TL;DR: This paper is a survey and an analysis of different ways of using deep learning (deep artificial neural networks) to generate musical content, based on the analysis of many existing deep-learning based systems for music generation selected from the relevant literature.
Proceedings Article
Counterpoint by Convolution
TL;DR: This model is an instance of orderless NADE, which allows more direct ancestral sampling, and finds that Gibbs sampling greatly improves sample quality, which is demonstrated to be due to some conditional distributions being poorly modeled.
Book ChapterDOI
Generating Polyphonic Music Using Tied Parallel Networks
TL;DR: A neural network architecture which enables prediction and composition of polyphonic music in a manner that preserves translation-invariance of the dataset and attains high performance at a musical prediction task and successfully creates note sequences which possess measure-level musical structure.
Journal ArticleDOI
A Functional Taxonomy of Music Generation Systems
TL;DR: A functional taxonomy for music generation systems with reference to existing systems is presented, which organizes systems according to the purposes for which they were designed and reveals the inter-relatedness amongst the systems.
Journal ArticleDOI
Conditional LSTM-GAN for Melody Generation from Lyrics
TL;DR: A novel deep generative model, conditional Long Short-Term Memory (LSTM)–Generative Adversarial Network for melody generation from lyrics is proposed, which contains a deep LSTM generator and a deep DSTM discriminator both conditioned on lyrics.
References
More filters
Journal ArticleDOI
A Generative Theory of Tonal Music
TL;DR: Aboitiz et al. as discussed by the authors explored the relationships between language, music, and the brain by pursuing four key themes and the crosstalk among them: song and dance as a bridge between music and language; multiple levels of structure from brain to behavior to culture; the semantics of internal and external worlds and the role of emotion; and the evolution and development of language.
Book
A Generative Theory of Tonal Music
Fred Lerdahl,Ray Jackendoff +1 more
TL;DR: Aboitiz et al. as discussed by the authors explored the relationships between language, music, and the brain by pursuing four key themes and the crosstalk among them: song and dance as a bridge between music and language; multiple levels of structure from brain to behavior to culture; the semantics of internal and external worlds and the role of emotion; and the evolution and development of language.
Book
The Algorithmic Beauty of Plants
TL;DR: Graphical modeling using L-systems and turtle interpretation of symbols for plant models and iterated function systems, and Fractal properties of plants.
Book
The origins of music.
TL;DR: Arom et al. as discussed by the authors presented the birth of evolutionary biomusicology and the evolution of the human musical behavior and the universal features of music and musical behavior across cultures.
Proceedings Article
GenJam: A Genetic Algorithm for Generating Jazz Solos
TL;DR: GenJam is a genetic algorithm-based model of a novice jazz musician learning to improvise that maintains hierarchically related populations of melodic ideas that are mapped to specific notes through scales suggested by the chord progression being played.