This book is a survey and analysis of how deep learning can be used to generate musical content. The authors offer a comprehensive presentation of the foundations of deep learning techniques for music generation. They also develop a conceptual framework used to classify and analyze various types of architecture, encoding models, generation strategies, and ways to control the generation. The five dimensions of this framework are: objective (the kind of musical content to be generated, e.g., melody, accompaniment); representation (the musical elements to be considered and how to encode them, e.g., chord, silence, piano roll, one-hot encoding); architecture (the structure organizing neurons, their connexions, and the flow of their activations, e.g., feedforward, recurrent, variational autoencoder); challenge (the desired properties and issues, e.g., variability, incrementality, adaptability); and strategy (the way to model and control the process of generation, e.g., single-step feedforward, iterative feedforward, decoder feedforward, sampling). To illustrate the possible design decisions and to allow comparison and correlation analysis they analyze and classify more than 40 systems, and they discuss important open challenges such as interactivity, originality, and structure. The authors have extensive knowledge and experience in all related research, technical, performance, and business aspects. The book is suitable for students, practitioners, and researchers in the artificial intelligence, machine learning, and music creation domains. The reader does not require any prior knowledge about artificial neural networks, deep learning, or computer music. The text is fully supported with a comprehensive table of acronyms, bibliography, glossary, and index, and supplementary material is available from the authors' website.

Computational approaches to music composition and style imitation have engaged musicians, music scholars, and computer scientists since the early days of computing. Music generation research has generally employed one of two strategies: knowledge-based methods that model style through explicitly formalized rules, and data mining methods that apply machine learning to induce statistical models of musical style. The five chapters in this book illustrate the range of tasks and design choices in current music generation research applying machine learning techniques and highlighting recurring research issues such as training data, music representation, candidate generation, and evaluation. The contributions focus on different aspects of modeling and generating music, including melody, chord sequences, ornamentation, and dynamics. Models are induced from audio data or symbolic data. This book was originally published as a special issue of the Journal of Mathematics and Music.

Design and use machine learning models for music generation using Magenta and make them interact with existing music creation tools Key FeaturesLearn how machine learning, deep learning, and reinforcement learning are used in music generationGenerate new content by manipulating the source data using Magenta utilities, and train machine learning models with itExplore various Magenta projects such as Magenta Studio, MusicVAE, and NSynthBook Description The importance of machine learning (ML) in art is growing at a rapid pace due to recent advancements in the field, and Magenta is at the forefront of this innovation. With this book, you’ll follow a hands-on approach to using ML models for music generation, learning how to integrate them into an existing music production workflow. Complete with practical examples and explanations of the theoretical background required to understand the underlying technologies, this book is the perfect starting point to begin exploring music generation. The book will help you learn how to use the models in Magenta for generating percussion sequences, monophonic and polyphonic melodies in MIDI, and instrument sounds in raw audio. Through practical examples and in-depth explanations, you’ll understand ML models such as RNNs, VAEs, and GANs. Using this knowledge, you’ll create and train your own models for advanced music generation use cases, along with preparing new datasets. Finally, you’ll get to grips with integrating Magenta with other technologies, such as digital audio workstations (DAWs), and using Magenta.js to distribute music generation apps in the browser. By the end of this book, you'll be well-versed with Magenta and have developed the skills you need to use ML models for music generation in your own style. What you will learnUse RNN models in Magenta to generate MIDI percussion, and monophonic and polyphonic sequencesUse WaveNet and GAN models to generate instrument notes in the form of raw audioEmploy Variational Autoencoder models like MusicVAE and GrooVAE to sample, interpolate, and humanize existing sequencesPrepare and create your dataset on specific styles and instrumentsTrain your network on your personal datasets and fix problems when training networksApply MIDI to synchronize Magenta with existing music production tools like DAWsWho this book is for This book is for technically inclined artists and musically inclined computer scientists. Readers who want to get hands-on with building generative music applications that use deep learning will also find this book useful. Although prior musical or technical competence is not required, basic knowledge of the Python programming language is assumed.

Generative modeling is one of the hottest topics in AI. It’s now possible to teach a machine to excel at human endeavors such as painting, writing, and composing music. With this practical book, machine-learning engineers and data scientists will discover how to re-create some of the most impressive examples of generative deep learning models, such as variational autoencoders,generative adversarial networks (GANs), encoder-decoder models and world models. Author David Foster demonstrates the inner workings of each technique, starting with the basics of deep learning before advancing to some of the most cutting-edge algorithms in the field. Through tips and tricks, you’ll understand how to make your models learn more efficiently and become more creative. Discover how variational autoencoders can change facial expressions in photos Build practical GAN examples from scratch, including CycleGAN for style transfer and MuseGAN for music generation Create recurrent generative models for text generation and learn how to improve the models using attention Understand how generative models can help agents to accomplish tasks within a reinforcement learning setting Explore the architecture of the Transformer (BERT, GPT-2) and image generation models such as ProGAN and StyleGAN

This book presents comprehensive coverage of the latest advances in research into enabling machines to listen to and compose new music. It includes chapters introducing what we know about human musical intelligence and on how this knowledge can be simulated with AI. The development of interactive musical robots and emerging new approaches to AI-based musical creativity are also introduced, including brain–computer music interfaces, bio-processors and quantum computing. Artificial Intelligence (AI) technology permeates the music industry, from management systems for recording studios to recommendation systems for online commercialization of music through the Internet. Yet whereas AI for online music distribution is well advanced, this book focuses on a largely unexplored application: AI for creating the actual musical content.

Algorithmic composition – composing by means of formalizable methods – has a century old tradition not only in occidental music history. This is the first book to provide a detailed overview of prominent procedures of algorithmic composition in a pragmatic way rather than by treating formalizable aspects in single works. In addition to an historic overview, each chapter presents a specific class of algorithm in a compositional context by providing a general introduction to its development and theoretical basis and describes different musical applications. Each chapter outlines the strengths, weaknesses and possible aesthetical implications resulting from the application of the treated approaches. Topics covered are: markov models, generative grammars, transition networks, chaos and self-similarity, genetic algorithms, cellular automata, neural networks and artificial intelligence are covered. The comprehensive bibliography makes this work ideal for the musician and the researcher alike.

This book constitutes the refereed proceedings of the 8th International Conference on Evolutionary Computation in Combinatorial Optimization, EvoMUSART 2019, held in Leipzig, Germany, in April 2019, co-located with the Evo*2019 events EuroGP, EvoCOP and EvoApplications. The 16 revised full papers presented were carefully reviewed and selected from 24 submissions. The papers cover a wide range of topics and application areas, including: visual art and music generation, analysis, and interpretation; sound synthesis; architecture; video; poetry; design; and other creative tasks.