A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset

Abstract

This paper proposes a new benchmark task for generat-ing musical passages in the audio domain by using thedrum loops from the FreeSound Loop Dataset, which arepublicly re-distributable. Moreover, we use a larger col-lection of drum loops from Looperman to establish fourmodel-based objective metrics for evaluation, releasingthese metrics as a library for quantifying and facilitatingthe progress of musical audio generation. Under this eval-uation framework, we benchmark the performance of threerecent deep generative adversarial network (GAN) mod-els we customize to generate loops, including StyleGAN,StyleGAN2, and UNAGAN. We also report a subjectiveevaluation of these models. Our evaluation shows that theone based on StyleGAN2 performs the best in both objec-tive and subjective metrics.

The paper has been accepted for publication at ISMIR 2021

References in corpus (11)

• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• GANSynth: Adversarial Neural Audio Synthesis
• MelNet: A Generative Model for Audio in the Frequency Domain
• Jukebox: A Generative Model for Music
• Evaluation of CNN-based Automatic Music Tagging Models
• Fréchet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms
• Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss
• MP3net: coherent, minute-long music generation from raw audio with a simple convolutional GAN
• A Minimal Template for Interactive Web-based Demonstrations of Musical Machine Learning
• DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the Loop