{"ID":2867500,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17375","arxiv_id":"2509.17375","title":"Improving Active Learning for Melody Estimation by Disentangling Uncertainties","abstract":"Estimating the fundamental frequency, or melody, is a core task in Music Information Retrieval (MIR). Various studies have explored signal processing, machine learning, and deep-learning-based approaches, with a very recent focus on utilizing uncertainty in active learning settings for melody estimation. However, these approaches do not investigate the relative effectiveness of different uncertainties. In this work, we follow a framework that disentangles aleatoric and epistemic uncertainties to guide active learning for melody estimation. Trained on a source dataset, our model adapts to new domains using only a small number of labeled samples. Experimental results demonstrate that epistemic uncertainty is more reliable for domain adaptation with reduced labeling effort as compared to aleatoric uncertainty.","short_abstract":"Estimating the fundamental frequency, or melody, is a core task in Music Information Retrieval (MIR). Various studies have explored signal processing, machine learning, and deep-learning-based approaches, with a very recent focus on utilizing uncertainty in active learning settings for melody estimation. However, these...","url_abs":"https://arxiv.org/abs/2509.17375","url_pdf":"https://arxiv.org/pdf/2509.17375v1","authors":"[\"Aayush Jaiswal\",\"Parampreet Singh\",\"Vipul Arora\"]","published":"2025-09-22T06:34:07Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false}