Research map / Learning theory and algorithms / Matrix and tensor methods
Optimal spectral transportation with application to music transcription
Rémi Flamary, Cédric Févotte, Nicolas Courty, Valentin Emiya
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 OST (Dirac dictionary) instead of PLCA with harmonic dictionary | OST · MAPS piano transcription, average | F-measure: 0.624 -> 0.563 | Hurt |
| use OST instead of PLCA, runtime | OST · MAPS piano transcription, average | unmixing time (s): 14.861 -> 0.004 | Improved |
| add entropy regularisation (OST_e) to OST (ablation) | OST · MAPS piano transcription, average | F-measure: 0.563 -> 0.673 | Improved |
| add flat noise component to OST_e (ablation) | OST_e · MAPS piano transcription, average | F-measure: 0.673 -> 0.684 | Improved |
| add flat noise component to OST (ablation) | OST · MAPS piano transcription, average | F-measure: 0.563 -> 0.612 | Improved |
| add flat noise component to PLCA (ablation) | PLCA · MAPS piano transcription, average | F-measure: 0.624 -> 0.619 | No clear effect |
| OST_e+noise instead of PLCA | OST_e+noise · MAPS piano transcription, average | F-measure: 0.624 -> 0.684 | Improved |
| OST_e+noise instead of PLCA, runtime | OST_e+noise · MAPS piano transcription, average | unmixing time (s): 14.861 -> 0.202 | Improved |
| group-regularised OST variants on shifted fundamentals | OST_g, OST_e+g · Toy simulated data scenario 1 | L1 error of activation | Improved |
| group-regularised OST variants on timbre variation | OST_g, OST_e+g · Toy simulated data scenario 2 | accuracy and run time | Improved |
| OST_e instead of PLCA on a single note | OST_e · Single piano note MIDI 50 | octave errors | Improved |
Closest papers by meaning
- Rubato: Transcribing Piano Music with Timestamps (NeurIPS 2026 · similarity 0.83)
- Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling (ICLR 2025 · similarity 0.83)
- Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training (NeurIPS 2026 · similarity 0.83)
- Multi-Source Diffusion Models for Simultaneous Music Generation and Separation (ICLR 2024 · similarity 0.82)
- DITTO: Diffusion Inference-Time T-Optimization for Music Generation (ICML 2024 · similarity 0.82)
- MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction (NeurIPS 2025 · similarity 0.82)
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.
