mlsanityData to 7 Oct 2026

SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment

arXiv 2604.25937 ↗First posted 16 Apr 2026eess.AS cs.AI cs.SDcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent advancements in Text-to-Song generation have enabled realistic musical content production, yet existing evaluation benchmarks lack the professional granularity to capture multi-dimensional aesthetic nuances. In this paper, we propose SongBench, a specialized framework for fine-grained song assessment across seven key dimensions: Vocal, Instrument, Melody, Structure, Arrangement, Mixing, and Musicality. Utilizing this framework, we construct an expert-annotated database comprising 11,717 samples from state-of-the-art models, labeled by music professionals. Extensive experimental results demonstrate that SongBench achieves high correlation with expert ratings. By revealing fine-grained performance gaps in current state-of-the-art models, SongBench serves as a diagnostic benchmark to steer the development toward more professional and musically coherent song generation.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

18 of 23 references.

References · 18

  1. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 707
  2. 2025Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Soundcited by 129
  3. 2024Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencentcited by 89
  4. 2021Generalization Ability of MOS Prediction Networkscited by 69
  5. 2025YuE: Scaling Open Foundation Models for Long-Form Music Generationcited by 68
  6. 2025MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantizationcited by 66
  7. 2025ACE-Step: A Step Towards Music Generation Foundation Modelcited by 54
  8. 2025DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusioncited by 46
  9. 2025SongEval: A Benchmark Dataset for Song Aesthetics Evaluationcited by 24
  10. 2025LeVo: High-Quality Song Generation with Multi-Preference Alignmentcited by 23
  11. 2026ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generationcited by 22
  12. 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinementcited by 21
6 more
  1. 2025MusicEval: A Generative Music Dataset with Expert Ratings for Automatic Text-to-Music Evaluationcited by 17
  2. 2025DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matchingcited by 14
  3. 2026HeartMuLa: A Family of Open Sourced Music Foundation Modelscited by 13
  4. 2023RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weightingcited by 6
  5. 2025SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcriptioncited by 5
  6. 2024Uncertainty-Aware Mean Opinion Score Predictioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Renderingcited by 1
  2. 2026StepAudio 3 Music Technical Reportcited by 1
  3. 2026WanSong v1.0 Technical Reportcited by 0
  4. 2026MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiquescited by 0
  5. 2026TTM-Bench: A Framework for Text-to-Music System Performance Benchmarkingcited by 0
  6. 2026MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intentcited by 0