Synopses & Reviews
Synopsis
This book describes how deep learning techniques can be used generate musical content of various types, including melodies, accompaniment, and chords.
Synopsis
This book is a survey and analysis of different ways of using deep learning, in particular deep artificial neural networks, to generate musical content. The authors propose a methodology based on five dimensions for analysis: objective, examples include melody, polyphony, accompaniment or counterpoint, performed by humans or machines; representation, i.e., the concepts to be manipulated (e.g., waveform, spectrogram, note, chord, meter, beat), the formats used (e.g., MIDI, piano roll, text), and the encodings; architecture, i.e., the types of deep neural network to be used, examples include feedforward network, recurrent network, autoencoder or generative adversarial networks; challenge, i.e., the limitations and open challenges, examples include variability, interactivity, and creativity; and finally strategy, i.e., how to model and control the process of generation, examples include single-step feedforward, iterative feedforward, sampling, and input manipulation. The book presents a comparative analysis of various models and techniques and proposes a bottom-up multidimensional typology.
The authors have extensive knowledge and experience in all related research, technical, performance, and business aspects, and the book is suitable for students, practitioners, and researchers in the artificial intelligence and music creation domains. The text is fully supported with a comprehensive table of acronyms, bibliography, glossary, and index, and supplementary material is available from the authors' website.
Synopsis
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.
Synopsis
Introduction.- Method.- Objective.- Representation.- Architecture.- Challenge and Strategy.- Analysis.- Discussion and Conclusion.