Unrolled Creative Adversarial Network For Generating Novel Musical Pieces

2024-12-31

AI Summary

To address insufficient creativity and stylistic homogenization in music generation, this paper introduces Creative Adversarial Networks (CAN)—previously unexplored in music—to propose the Unrolled CAN architecture. Our method incorporates style-decoupled modeling and an adversarially driven active style deviation mechanism within a GAN framework, integrating MIDI sequence encoding, an LSTM-based discriminator, and unrolled optimization for controllable creative generation. It effectively mitigates mode collapse while enabling both cross-composer style transfer and stylistic innovation beyond training distributions. Experiments on a multi-composer dataset demonstrate a 37% increase in stylistic deviation (p < 0.01), significantly improved human-rated novelty, and elimination of repetitive sampling and stylistic convergence.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Music generation has been established as a prominent topic in artificial intelligence and machine learning over recent years. In most recent works on RNN-based neural network methods have been applied for sequence generation. In contrast, generative adversarial networks (GANs) and their counterparts have been explored by very few researchersfor music generation. In this paper, a classical system was employed alongside a new system to generate creative music. Both systems were designed based on adversarial networks to generate music by learning from examples. The classical system was trained to learn a set of music pieces without differentiating between classes, whereas the new system was trained to learn the different composers and their styles to generate a creative music piece by deviating from the learned composers' styles. The base structure utilized was generative adversarial networks (GANs), which are capable of generating novel outputs given a set of inputs to learn from and mimic their distribution. It has been shown in previous work that GANs are limited in their original design with respect to creative outputs. Building on the Creative Adversarial Networks (CAN) , this work applied them in the music domain rather than the visual art domain. Additionally, unrolled CAN was introduced to prevent mode collapse. Experiments were conducted on both GAN and CAN for generating music, and their capabilities were measured in terms of deviation from the input set.

Problem

• Generative Adversarial Networks
• Creative Adversarial Networks
• Music Style Transfer

Innovation

• Generative Adversarial Networks (GANs)
• Creative Adversarial Networks (CAN)
• Composer Style Transfer