Latest Research in Generative Music Modeling

Top Research Topics in Generative Music Modeling

• Sound — 71 papers
• Music and Audio Processing — 18 papers
• Audio and Speech Processing — 16 papers
• Computer Vision and Pattern Recognition — 9 papers
• Topic Modeling — 6 papers
• Computation and Language — 5 papers
• Music Technology and Sound Studies — 4 papers
• Neuroscience and Music Perception — 2 papers
• Multimedia — 2 papers
• Machine Learning — 2 papers

Highest-Cited Papers

1. Explicit Note-Event Tokenization and Pitch-Validity Constrained Decoding for MIDI-to-Tablature Transcription
2. MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation
3. Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory
4. Text2Score: Generating Sheet Music From Textual Prompts
5. Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering
6. Detection of AI-generated stems within hybrid human-AI music
7. Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding
8. Transformer-Based Rhythm Quantization of Performance MIDI Using Beat Annotations
9. Finding the noise: Zero-shot AI Music Detection
10. Spacing Out: On the Reliability of Binaural Music Source Separation Metrics
11. Emotion-aware Multimodal Music Recommendation via Semantic Image-audio Alignment
12. Text-Prompted CLAP: Learning Query-Conditioned Audio Representations via Contrastive Learning
13. Qwen-Music Technical Report
14. OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation
15. Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models
16. Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models
17. Reflector: Arrangement-Aware Harmonic Retrieval for Sample-Based Composition
18. StemFX: Learning Mixing Style Representations via Autoregressive FX Chain Prediction on Source-Separated Stems
19. Music-JEPA: Learning a World Model of Sound from Action
20. CODA: Cascaded Online Discontinuity-Aware Alignment for Real-Time Image-Based Score Following

Sub-Regions

• Sound — 108 papers
• Audio and Speech Processing — 24 papers
• Topic Modeling — 13 papers