Text-to-music Generation via Structured Captions AND Interpretable Evaluation
cs.SD, eess.AS
Submitted: 2026-10-31
Updated: 2026-10-31
Project page: https://mu-scap.github.io
Terminology
Sources
- MusicLM: Generating Music From Text
- Stable Audio 3
- Seed-Music: A Unified Framework for High Quality and Controlled Music Generation
- ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation
- Qwen-Music Technical Report
- MusicEval: A Generative Music Dataset with Expert Ratings for Automatic Text-to-Music Evaluation
- CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction
- AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering
- AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following
- AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation
- Qwen2.5-Omni Technical Report
- Music Flamingo: Scaling Music Understanding in Audio Language Models
- MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems