{"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/city-classification-from-multiple-real-world","title":"City classification from multiple real-world sound scenes","arxiv_id":"1905.00979","date":"2019-07-29","proceeding":null,"authors":[],"abstract":"The majority of sound scene analysis work focuses on one of two clearly\ndefined tasks: acoustic scene classification or sound event detection. Whilst\nthis separation of tasks is useful for problem definition, they inherently\nignore some subtleties of the real-world, in particular how humans vary in how\nthey describe a scene. Some will describe the weather and features within it,\nothers will use a holistic descriptor like `park', and others still will use\nunique identifiers such as cities or names. In this paper, we undertake the\ntask of automatic city classification to ask whether we can recognize a city\nfrom a set of sound scenes? In this problem each city has recordings from\nmultiple scenes. We test a series of methods for this novel task and show that\na simple convolutional neural network (CNN) can achieve accuracy of 50%. This\nis less than the acoustic scene classification task baseline in the DCASE 2018\nASC challenge on the same data. A simple adaptation to the class labels of\npairing city labels with grouped scenes, accuracy increases to 52%, closer to\nthe simpler scene classification task. Finally we also formulate the problem in\na multi-task learning framework and achieve an accuracy of 56%, outperforming\nthe aforementioned approaches.","url_abs":"http://arxiv.org/abs/1905.00979v2","url_pdf":"http://arxiv.org/pdf/1905.00979v2.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":"city-classification-from-multiple-real-world","repo_url":"https://github.com/drylbear/soundscapeCityClassification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"acoustic-scene-classification","task_name":"Acoustic Scene Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"scene-classification","task_name":"Scene Classification"},{"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}