Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss

2020/11/25 by Nao Tokui, Tokui, Nao
Computer Science · #00A65 #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #H.5.5 #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #acm:00A65 #cs.AI #cs.SD #msc:00A65

paper · pdf · doi:10.48550/arxiv.2011.13062

arxiv created 2020/11/25 · openalex publication_date 2020/11/25 · arxiv updated 2020/11/30 · openalex created_date 2020/12/07 · openalex updated_date 2026/07/28

Abstract

Since the introduction of deep learning, researchers have proposed content generation systems using deep learning and proved that they are competent to generate convincing content and artistic output, including music. However, one can argue that these deep learning-based systems imitate and reproduce the patterns inherent within what humans have created, instead of generating something new and creative. This paper focuses on music generation, especially rhythm patterns of electronic dance music, and discusses if we can use deep learning to generate novel rhythms, interesting patterns not found in the training dataset. We extend the framework of Generative Adversarial Networks(GAN) and encourage it to diverge from the dataset's inherent distributions by adding additional classifiers to the framework. The paper shows that our proposed GAN can generate rhythm patterns that sound like music rhythms but do not belong to any genres in the training dataset. The source code, generated rhythm patterns, and a supplementary plugin software for a popular Digital Audio Workstation software are available on our website.

Citations

• Long Short-Term Memory
• Conditional Generative Adversarial Nets
• Text-based LSTM networks for Automatic Music Composition
• C-RNN-GAN: Continuous recurrent neural networks with adversarial training
• CAN: Creative Adversarial Networks, Generating "Art" by Learning About\n Styles and Deviating from Style Norms

Related

• Off the Beaten Track: Using Deep Learning to Interpolate Between Music Genres
• Unrolled Creative Adversarial Network For Generating Novel Musical Pieces
• From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends
• Quantized GAN for Complex Music Generation from Dance Videos
• MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation