Research map / Image generation / Editing and style transfer
Play as You Like: Timbre-Enhanced Multi-Modal Music Style Transfer
Chien-Yu Lu, Min-Xin Xue, Chia-Che Chang, Che-Rung Lee, Li Su
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 MUNIT-MS instead of CycleGAN-MS | Music style transfer · Four transfer tasks (Average) | ST MOS: 2.90 -> 3.12 | Improved |
| Use MUNIT-MS instead of CycleGAN-MS | Music style transfer · Four transfer tasks (Average) | CP MOS: 3.99 -> 3.72 | Hurt |
| Use MUNIT-MS instead of CycleGAN-MS | Music style transfer · Four transfer tasks (Average) | SQ MOS: 2.64 -> 2.61 | No clear effect |
| Add MFCC, spectral difference, and spectral envelope channels to the mel-spectrogram input (ablation) | MUNIT music style transfer · Four transfer tasks (Average) | SQ MOS: 2.61 -> 2.82 | Improved |
| Add MFCC, spectral difference, and spectral envelope channels to the mel-spectrogram input (ablation) | MUNIT music style transfer · Four transfer tasks (Average) | ST MOS: 3.12 -> 3.09 | No clear effect |
| Use all four audio feature channels instead of mel-spectrogram and MFCC (ablation) | MUNIT music style transfer · Four transfer tasks (Average) | SQ MOS: 2.69 -> 2.82 | Improved |
| Use all four audio feature channels instead of mel-spectrogram and MFCC (ablation) | MUNIT music style transfer · Piano to string quartet (P2S) | ST MOS: 2.77 -> 2.12 | Hurt |
| Use all four audio feature channels instead of mel-spectrogram and MFCC (ablation) | MUNIT music style transfer · Piano to guitar (P2G) | ST MOS: 3.30 -> 3.55 | Improved |
| Use MUNIT rather than CycleGAN | Music style transfer · Four transfer tasks (Average) | ST MOS: 2.90 -> 3.12 | Improved |
| Use MUNIT rather than CycleGAN | Music style transfer · Four transfer tasks (Average) | CP MOS: 3.99 -> 3.72 | Hurt |
Closest papers by meaning
- Music Style Transfer with Time-Varying Inversion of Diffusion Models (AAAI 2024 · similarity 0.91)
- Deep Learning for Style Transfer and Experimentation with Audio Effects and Music Creation (AAAI 2024 · similarity 0.87)
- MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music Composition (AAAI 2025 · similarity 0.86)
- MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models (CVPR 2024 · similarity 0.85)
- Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling (NeurIPS 2024 · similarity 0.85)
- MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence (NeurIPS 2024 · similarity 0.85)
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.
