{"ID":2887703,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01493","arxiv_id":"2508.01493","title":"Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport","abstract":"In this paper, we propose an Optimal Transport objective for learning one-dimensional translation-equivariant systems and demonstrate its applicability to single pitch estimation. Our method provides a theoretically grounded, more numerically stable, and simpler alternative for training state-of-the-art self-supervised pitch estimators.","short_abstract":"In this paper, we propose an Optimal Transport objective for learning one-dimensional translation-equivariant systems and demonstrate its applicability to single pitch estimation. Our method provides a theoretically grounded, more numerically stable, and simpler alternative for training state-of-the-art self-supervised...","url_abs":"https://arxiv.org/abs/2508.01493","url_pdf":"https://arxiv.org/pdf/2508.01493v1","authors":"[\"Bernardo Torres\",\"Alain Riou\",\"Gaël Richard\",\"Geoffroy Peeters\"]","published":"2025-08-02T21:31:14Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\",\"cs.LG\",\"eess.AS\"]","methods":"[]","has_code":false}