MorpheuS: generating structured music with constrained patterns and tension

Abstract

Automatic music generation systems have gained in popularity and sophistication as advances in cloud computing have enabled large-scale complex computations such as deep models and optimization algorithms on personal devices. Yet, they still face an important challenge, that of long-term structure, which is key to conveying a sense of musical coherence. We present the MorpheuS music generation system designed to tackle this problem. MorpheuS' novel framework has the ability to generate polyphonic pieces with a given tension profile and long- and short-term repeated pattern structures. A mathematical model for tonal tension quantifies the tension profile and state-of-the-art pattern detection algorithms extract repeated patterns in a template piece. An efficient optimization metaheuristic, variable neighborhood search, generates music by assigning pitches that best fit the prescribed tension profile to the template rhythm while hard constraining long-term structure through the detected patterns. This ability to generate affective music with specific tension profile and long-term structure is particularly useful in a game or film music context. Music generated by the MorpheuS system has been performed live in concerts.

IEEE Transactions on Affective Computing. PP(99)

References in corpus (5)

• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
• AI Methods in Algorithmic Composition: A Comprehensive Survey
• A Functional Taxonomy of Music Generation Systems
• Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints
• From Bach to the Beatles: The simulation of human tonal expectation using ecologically-trained predictive models

Cited by in corpus (11)

• A Functional Taxonomy of Music Generation Systems
• Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model
• A variational autoencoder for music generation controlled by tonal tension
• Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling
• The Beauty of Repetition in Machine Composition Scenarios
• A New Corpus for Computational Music Research and A Novel Method for Musical Structure Analysis
• An Exploratory Study on Perceptual Spaces of the Singing Voice
• Spectrogram Inpainting for Interactive Generation of Instrument Sounds
• Hierarchical Recurrent Neural Networks for Conditional Melody Generation with Long-term Structure
• aiSTROM -- A roadmap for developing a successful AI strategy
• Musical Speech: A Transformer-based Composition Tool