{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/polyphonic-sound-event-detection-by-using","title":"Polyphonic Sound Event Detection by using Capsule Neural Network","arxiv_id":"1810.06325","date":"2018-10-15","proceeding":null,"authors":["Fabio Vesperini","Leonardo Gabrielli","Emanuele Principi","Stefano Squartini"],"abstract":"Artificial sound event detection (SED) has the aim to mimic the human ability\nto perceive and understand what is happening in the surroundings. %\nenvironment. Nowadays, Deep Learning offers valuable techniques for this goal\nsuch as Convolutional Neural Networks (CNNs). The Capsule Neural Network\n(CapsNet) architecture has been recently introduced in the image processing\nfield with the intent to overcome some of the known limitations of CNNs,\nspecifically regarding the scarce robustness to affine transformations (i.e.,\nperspective, size, orientation) and the detection of overlapped images. This\nmotivated the authors to employ CapsNets to deal with the polyphonic-SED task,\nin which multiple sound events occur simultaneously. Specifically, we propose\nto exploit the capsule units to represent a set of distinctive properties for\neach individual sound event. Capsule units are connected through a so-called\n\\textit{dynamic routing} that encourages learning part-whole relationships and\nimproves the detection performance in a polyphonic context. This paper reports\nextensive evaluations carried out on three publicly available datasets, showing\nhow the CapsNet-based algorithm not only outperforms standard CNNs but also\nallows to achieve the best results with respect to the state of the art\nalgorithms.","url_abs":"http://arxiv.org/abs/1810.06325v1","url_pdf":"http://arxiv.org/pdf/1810.06325v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"polyphonic-sound-event-detection-by-using","repo_url":"https://gitlab.com/a3labShares/capsule-for-sed","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"sound-event-detection","task_name":"Sound Event Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}