{"ID":2898363,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.03482","arxiv_id":"2507.03482","title":"OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction","abstract":"Developing open-source foundation models is essential for advancing research in music audio understanding and ensuring access to powerful, multipurpose representations for music information retrieval. We present OMAR-RQ, a model trained with self-supervision via masked token classification methodologies using a large-scale dataset with over 330,000 hours of music audio. We experiment with different input features and quantization options, and achieve state-of-the-art performance in music tagging, pitch estimation, chord recognition, beat tracking, segmentation, and difficulty estimation among open self-supervised models. We open-source our training and evaluation pipelines and model weights, available at https://github.com/mtg/omar-rq.","short_abstract":"Developing open-source foundation models is essential for advancing research in music audio understanding and ensuring access to powerful, multipurpose representations for music information retrieval. We present OMAR-RQ, a model trained with self-supervision via masked token classification methodologies using a large-s...","url_abs":"https://arxiv.org/abs/2507.03482","url_pdf":"https://arxiv.org/pdf/2507.03482v1","authors":"[\"Pablo Alonso-Jiménez\",\"Pedro Ramoneda\",\"R. Oguz Araz\",\"Andrea Poltronieri\",\"Dmitry Bogdanov\"]","published":"2025-07-04T11:19:47Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false,"code_links":[{"ID":612405,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2898363,"paper_url":"https://arxiv.org/abs/2507.03482","paper_title":"OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction","repo_url":"https://github.com/mtg/omar-rq","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}