6 papers
Difficulty-Controlled Simplification of Piano Scores with Synthetic Data for Inclusive Music Education
Pedro Ramoneda, Emilia Parada-Cabaleiro, Dasaem Jeong +1
Despite its potential, AI advances in music education are hindered by proprietary systems that limit the democratization of technology in this domain. In particular, AI-driven musi…
Difficulty-Aware Score Generation for Piano Sight-Reading
Pedro Ramoneda, Masahiro Suzuki, Akira Maezawa +1
Adapting learning materials to the level of skill of a student is important in education. In the context of music training, one essential ability is sight-reading -- playing unfami…
Benchmarking Music Autotagging with MGPHot Expert Annotations vs. Generic Tag Datasets
Pedro Ramoneda, Pablo Alonso-Jiménez, Sergio Oramas +2
Music autotagging aims to automatically assign descriptive tags, such as genre, mood, or instrumentation, to audio recordings. Due to its challenges, diversity of semantic descript…
OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction
Pablo Alonso-Jiménez, Pedro Ramoneda, R. Oguz Araz +2
Developing open-source foundation models is essential for advancing research in music audio understanding and ensuring access to powerful, multipurpose representations for music in…
Can Audio Reveal Music Performance Difficulty? Insights from the Piano Syllabus Dataset
Pedro Ramoneda, Minhee Lee, Dasaem Jeong +2
Automatically estimating the performance difficulty of a music piece represents a key process in music education to create tailored curricula according to the individual needs of t…
Music Proofreading with RefinPaint: Where and How to Modify Compositions given Context
Pedro Ramoneda, Martin Rocamora, Taketo Akama
Autoregressive generative transformers are key in music generation, producing coherent compositions but facing challenges in human-machine collaboration. We propose RefinPaint, an…