{"ID":2858488,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12819","arxiv_id":"2510.12819","title":"Beyond Discrete Categories: Multi-Task Valence-Arousal Modeling for Pet Vocalization Analysis","abstract":"Traditional pet emotion recognition from vocalizations, based on discrete classification, struggles with ambiguity and capturing intensity variations. We propose a continuous Valence-Arousal (VA) model that represents emotions in a two-dimensional space. Our method uses an automatic VA label generation algorithm, enabling large-scale annotation of 42,553 pet vocalization samples. A multi-task learning framework jointly trains VA regression with auxiliary tasks (emotion, body size, gender) to enhance prediction by improving feature learning. Our Audio Transformer model achieves a validation Valence Pearson correlation of r = 0.9024 and an Arousal r = 0.7155, effectively resolving confusion between discrete categories like \"territorial\" and \"happy.\" This work introduces the first continuous VA framework for pet vocalization analysis, offering a more expressive representation for human-pet interaction, veterinary diagnostics, and behavioral training. The approach shows strong potential for deployment in consumer products like AI pet emotion translators.","short_abstract":"Traditional pet emotion recognition from vocalizations, based on discrete classification, struggles with ambiguity and capturing intensity variations. We propose a continuous Valence-Arousal (VA) model that represents emotions in a two-dimensional space. Our method uses an automatic VA label generation algorithm, enabl...","url_abs":"https://arxiv.org/abs/2510.12819","url_pdf":"https://arxiv.org/pdf/2510.12819v1","authors":"[\"Junyao Huang\",\"Rumin Situ\"]","published":"2025-10-09T23:39:40Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\",\"eess.AS\"]","methods":"[\"Transformer\"]","has_code":false}