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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhung2021a

Related papers

• Exploiting Pre-trained Feature Networks For Generative Adversarial Networks In Audio-domain Loop Generation (2022)0.00
• Collaborative Learning To Generate Audio-video Jointly (2021)7.16
• Musicldm: Enhancing Novelty In Text-to-music Generation Using Beat-synchronous Mixup Strategies (2023)13.55
• Incorporating Music Knowledge In Continual Dataset Augmentation For Music Generation (2020)0.00
• Audiobench: A Universal Benchmark For Audio Large Language Models (2024)10.21
• Synthesising Handwritten Music With Gans: A Comprehensive Evaluation Of Cyclewgan, Progan, And DCGAN (2024)3.58
• Savgbench: Benchmarking Spatially Aligned Audio-video Generation (2024)0.00
• Unconditional Audio Generation With Generative Adversarial Networks And Cycle Regularization (2020)9.41