Benchmarking Music Generation Models and Metrics via Human Preference Studies


Loading...

Date

2024-12-14

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Recent advancements have brought generated music closer to human-created compositions, yet evaluating these models remains challenging. While human preference is the gold standard for assessing quality, translating these subjective judgments into objective metrics, particularly for text-audio alignment and music quality, has proven difficult. In this work, we generate 6k songs using 12 state-of-the-art models and conduct a survey of 15k pairwise audio comparisons with 2.5k human participants to evaluate the correlation between human preferences and widely used metrics. To the best of our knowledge, this work is the first to rank current state-of-the-art music generation models and metrics based on human preference. To further the field of subjective metric evaluation, we provide open access to our dataset of generated music and human evaluations.

Publication status

published

Editor

Book title

Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation

Journal / series

Volume

Pages / Article No.

Publisher

OpenReview

Event

Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03604 - Wattenhofer, Roger / Wattenhofer, Roger check_circle

Notes

Poster presentation on December 14, 2024.

Funding

Related publications and datasets