mlsanityData to 14 Oct 2026

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

arXiv 2502.05139 ↗First posted 7 Feb 2025cs.SD cs.LG eess.AScited by 137

Not on the map. Why?

Cited by 29 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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 depend on human listeners for evaluation, leading to inconsistencies and high resource demands. This paper addresses the growing need for automated systems capable of predicting audio aesthetics without human intervention. Such systems are crucial for applications like data filtering, pseudo-labeling large datasets, and evaluating generative audio models, especially as these models become more sophisticated. In this work, we introduce a novel approach to audio aesthetic evaluation by proposing new annotation guidelines that decompose human listening perspectives into four distinct axes. We develop and train no-reference, per-item prediction models that offer a more nuanced assessment of audio quality. Our models are evaluated against human mean opinion scores (MOS) and existing methods, demonstrating comparable or superior performance. This research not only advances the field of audio aesthetics but also provides open-source models and datasets to facilitate future work and benchmarking. We release our code and pre-trained model at: https://github.com/facebookresearch/audiobox-aesthetics

Key facts. Cited by 137 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Feb 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 47; 2026: 90.

137 papers.

Sort:

By area:

  1. 2025UniVerse-1: Unified Audio-Video Generation via Stitching of Expertscited by 61
  2. 2025ACE-Step: A Step Towards Music Generation Foundation Modelcited by 56
  3. 2026MOVA: Towards Scalable and Synchronized Video-Audio Generationcited by 43
  4. 2025UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactionscited by 38
  5. 2025VABench: A Comprehensive Benchmark for Audio-Video Generationcited by 30
  6. 2025SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generationcited by 29
  7. 2025AudioX: A Unified Framework for Anything-to-Audio Generationcited by 27
  8. 2025LeVo: High-Quality Song Generation with Multi-Preference Alignmentcited by 25
  9. 2026JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generationcited by 25
  10. 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinementcited by 23
  11. 2026AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generationcited by 21
  12. 2026DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generationcited by 20
38 more
  1. 2025Audio-Sync Video Generation with Multi-Stream Temporal Controlcited by 15
  2. 2025DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matchingcited by 15
  3. 2025SpeechJudge: Towards Human-Level Judgment for Speech Naturalnesscited by 15
  4. 2025Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generationcited by 14
  5. 2026MOSS-TTS Technical Reportcited by 14
  6. 2026Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillationcited by 13
  7. 2026Omni2Sound: Towards Unified Video-Text-to-Audio Generationcited by 11
  8. 2025UALM: Unified Audio Language Model for Understanding, Generation and Reasoningcited by 10
  9. 2025Towards Interactive Intelligence for Digital Humanscited by 10
  10. 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 10
  11. 2025PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generationcited by 9
  12. 2025AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refinercited by 9
  13. 2025Analysis and Evaluation of Synthetic Data Generation in Speech Dysfluency Detectioncited by 8
  14. 2025TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systemscited by 8
  15. 2026Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Controlcited by 8
  16. 2026SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessmentcited by 7
  17. 2026OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generationcited by 7
  18. 2026Native Audio-Visual Alignment for Generationcited by 7
  19. 2025SonicMaster: Towards Controllable All-in-One Music Restoration and Masteringcited by 6
  20. 2025EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generationcited by 6
  21. 2026The Design Space of Tri-Modal Masked Diffusion Modelscited by 6
  22. 2026MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluationcited by 6
  23. 2026CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generationcited by 6
  24. 2026UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gatingcited by 6
  25. 2026MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generationcited by 6
  26. 2025MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generationcited by 5
  27. 2026InstructAV2AV: Instruction-Guided Audio-Video Joint Editingcited by 5
  28. 2026VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generationcited by 5
  29. 2025A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generationcited by 4
  30. 2025UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoEcited by 4
  31. 2025Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Videocited by 4
  32. 2025SAO-Instruct: Free-form Audio Editing using Natural Language Instructionscited by 4
  33. 2025MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generationcited by 4
  34. 2026Bagpiper: Solving Open-Ended Audio Tasks via Rich Captionscited by 4
  35. 2026TADA! Tuning Audio Diffusion Models through Activation Steeringcited by 4
  36. 2026GSRM: Generative Speech Reward Model for Speech RLHFcited by 4
  37. 2026Improving Joint Audio-Video Generation with Cross-Modal Context Learningcited by 4
  38. 2026Baton: Explicit Semantic Blueprints for Joint Video-Audio Generationcited by 4

50 most cited of 137 All 137 (JSON)