paper-with-me

홈 › Papers

MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations

2026-07-08 · Sirui Zhang, Tianle Wang, Xinyi Tong, Peiyang Yu, Jishang Chen, Liangke Zhao, Haoxin Zhang, Duo Xu, Xin Jin, Feng Yu, Songchun Zhu arxiv

Music aesthetic assessment is a challenging yet underexplored problem, requiring models to capture fine-grained, multi-dimensional human perceptual judgments. Progress in this area has been limited by the lack of large-scale datasets with structured aesthetic annotations. We introduce MADB, a large-scale dataset and benchmark comprising 9,999 tracks annotated by 30 trained annotators. Each track is rated by around 10 annotators across 10 perceptual dimensions and one overall score, with additional textual comments for multimodal analysis. We establish a unified evaluation framework over multiple pretrained models. Results reveal substantial gaps between model predictions and human judgments, exposing key limitations of current approaches. MADB provides a new benchmark for human-aligned music understanding. Project page: https://github.com/knownree/madb

📄 PDF Abstract BibTeX arXiv:2607.06929

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SongEval: A Benchmark Dataset for Song Aesthetics Evaluation

2025-05-16 · Jixun Yao, Guobin Ma, Huixin Xue, Huakang Chen 외

Aesthetics serve as an implicit and important criterion in song generation tasks that reflect human perception beyond objective metrics. However, evaluating the aesthetics of generated songs remains a fundamental challen…

LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training

2026-06-29 · Shun Lei, Huaicheng Zhang, Dapeng Wu, Yaoxun Xu 외 arxiv

Full-length song generation must preserve coherence and musicality, render detailed vocal and accompaniment acoustics, and follow lyrics and prompts. Existing language model-based systems face a structural trade-off: mix…

From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training

2025-06-20 · Mingyang Yao, Ke Chen

Despite progress in controllable symbolic music generation, data scarcity remains a challenge for certain control modalities. Composer-style music generation is a prime example, as only a few pieces per composer are avai…

Music GenerationRhythm

An Order-Complexity Model for Aesthetic Quality Assessment of Homophony Music Performance

2023-04-23 · Xin Jin, Wu Zhou, Jinyu Wang, Duo Xu 외

Although computational aesthetics evaluation has made certain achievements in many fields, its research of music performance remains to be explored. At present, subjective evaluation is still a ultimate method of music a…

Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound

2025-02-07 · Andros Tjandra, Yi-Chiao Wu, Baishan Guo, John Hoffman 외

The quantification of audio aesthetics remains a complex challenge in audio processing, primarily due to its subjective nature, which is influenced by human perception and cultural context. Traditional methods often depe…

Benchmarking