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

2021/08/03 by Tun-Min Hung, Hung, Tun-Min, Bo-Yu Chen +7
Computer Science · Engineering · #Generative Adversarial Networks and Image Synthesis #Music Technology and Sound Studies #Music and Audio Processing #cs.SD #eess.AS

paper · pdf · doi:10.48550/arxiv.2108.01576

The paper has been accepted for publication at ISMIR 2021

arxiv created 2022/09/22 · arxiv updated 2022/09/23

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.

Related

• LoopNet: Musical Loop Synthesis Conditioned On Intuitive Musical Parameters
• Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop Generation
• LoopGen: Training-Free Loopable Music Generation
• The Freesound Loop Dataset and Annotation Tool
• A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions