Algorithmic Composition of Melodies with Deep Recurrent Neural Networks

arXiv.org Machine Learning

A big challenge in algorithmic composition is to devise a model that is both easily trainable and able to reproduce the long-range temporal dependencies typical of music. Here we investigate how artificial neural networks can be trained on a large corpus of melodies and turned into automated music composers able to generate new melodies coherent with the style they have been trained on. We employ gated recurrent unit networks that have been shown to be particularly efficient in learning complex sequential activations with arbitrary long time lags. Our model processes rhythm and melody in parallel while modeling the relation between these two features. Using such an approach, we were able to generate interesting complete melodies or suggest possible continuations of a melody fragment that is coherent with the characteristics of the fragment itself.


Algorithmically Flexible Style Composition Through Multi-Objective Fitness Functions

AAAI Conferences

Creating a musical fitness function is largely subjective and can be critically affected by the designer's biases. Previous attempts to create such functions for use in genetic algorithms lack scope or are prejudiced to a certain genre of music. They also are limited to producing music strictly in the style determined by the programmer. We show in this paper that musical feature extractors, which avoid the challenges of qualitative judgment, enable creation of a multi-objective function for direct music production. The main result is that the multi-objective fitness function enables creation of music with varying identifiable styles. To demonstrate this, we use three different multi-objective fitness functions to create three distinct sets of musical melodies. We then evaluate the distinctness of these sets using three different approaches: a set of traditional computational clustering metrics; a survey of non-musicians; and analysis by three trained musicians.


Worldwide AI

AI Magazine

Neuromorphic, evolutionary, or fuzzylike systems have been developed by many research groups in the Spanish computer sciences. It is no surprise, then, that these naturegrounded efforts start to emerge, enriching the AI catalogue of research projects and publications and, eventually, leading to new directions of basic or applied research. In this article, we review the contribution of Melomics in computational creativity. In Spain there are 74 universities, many of which have computer science departments that host AIrelated research groups. AEPIA, the Spanish society for AI research, was founded in 1983 and has been vigorously promoting the advancement of AI since then. Along with several other societies and communities of interest, it promotes various periodic conferences and workshops. The Artificial Intelligence Research Institute (IIIA) of the Spanish National Research Council constitutes one of the flagships of local AI research. Ramón López de Mántaras, IIIA's renowned director, was one of the pioneers of AI in Spain, and he also was the recipient of the prestigious AAAI Englemore Award in 2011. Other researchers that have reached an outstanding position, and lead important research groups in Spain, include Antonio Bahamonde (University of Oviedo), Federico Barber (Polytechnic University of Madrid), Vicent Botti (Polytechnic University of Valencia), and Amparo Vila (University of Granada). This department, with more than one hundred faculty members, is organized in several research groups, three of which maintain active AI research lines. Melomics is a new approach in artificial creativity (for a perspective on this discipline, see the 2009 fall issue of AI Magazine). More specifically, it focuses on algorithmic composition and aims at the full automation of the composition process of professional music.


Melomics: A Case-Study of AI in Spain

AI Magazine

Traditionally focused on good old-fashioned AI and robotics, the Spanish AI community holds a vigorous computational intelligence substrate. Neuromorphic, evolutionary, or fuzzylike systems have been developed by many research groups in the Spanish computer sciences. It is no surprise, then, that these naturegrounded efforts start to emerge, enriching the AI catalogue of research projects and publications and, eventually, leading to new directions of basic or applied research. In this article, we review the contribution of Melomics in computational creativity.


EuroGP2006 & EvoCOP2006, incorporating EvoWorkshops2006

AITopics Original Links

The application of Evolutionary Computation (EC) techniques for the development of creative systems is a new, exciting and significant area of research. There is a growing interest in the application of these techniques in fields such as: art and music generation, analysis and interpretation; architecture; and design. EvoMUSART 2006 is the third workshop of the EvoNet working group on Evolutionary Music and Art. Following the success of previous events, the main goal of EvoMUSART 2006 is to bring together researchers who are using Evolutionary Computation in this context, providing the opportunity to promote, present and discuss ongoing work in the area. The workshop will include an open panel for the discussion of the most relevant questions of the field.