Research map / Image generation / GANs
MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use shared inter-track noise and a collective discriminator instead of independent track generators | MuseGAN from-scratch generation · LPD-5-cleansed | TD B-G: 1.56 -> 1.34 | Helped |
| Use a collective generator/discriminator rather than independent track generators | MuseGAN from-scratch generation · LPD-5-cleansed | Harmonious rating: 2.83 -> 3.15 | Helped |
| Use independent private generators for each track | MuseGAN from-scratch generation · LPD-5-cleansed | QN bass (%): 90.0 -> 71.5 | Mixed |
| Remove batch normalization layers (ablation) | MuseGAN composer · LPD-5-cleansed, from scratch | QN bass (%): 49.5 -> 0.00 | Hurt |
| Use hybrid generation instead of composer generation | MuseGAN, from-scratch generation · LPD-5-cleansed | TD B-G: 1.37 -> 1.34 | Helped |
| Use hybrid generation instead of jamming generation | MuseGAN, track-conditional generation · LPD-5-cleansed | Overall rating, pro listeners: 2.69 -> 2.70 | No clear effect |
| Use jamming generation instead of composer or hybrid generation | MuseGAN, track-conditional generation · LPD-5-cleansed | Overall rating, non-pro listeners: 2.89 vs 2.70 and 3.01 | Helped |
Closest papers by meaning
- JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation (AAAI 2025 · similarity 0.89)
- Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models (ICLR 2024 · similarity 0.88)
- Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation (ICML 2025 · similarity 0.88)
- MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music Composition (AAAI 2025 · similarity 0.88)
- Compose with Me: Collaborative Music Inpainter for Symbolic Music Infilling (AAAI 2025 · similarity 0.87)
- MuPT: A Generative Symbolic Music Pretrained Transformer (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.