{"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/localization-detection-and-tracking-of","title":"Localization, Detection and Tracking of Multiple Moving Sound Sources with a Convolutional Recurrent Neural Network","arxiv_id":"1904.12769","date":"2019-04-29","proceeding":null,"authors":["Sharath Adavanne","Archontis Politis","Tuomas Virtanen"],"abstract":"This paper investigates the joint localization, detection, and tracking of\nsound events using a convolutional recurrent neural network (CRNN). We use a\nCRNN previously proposed for the localization and detection of stationary\nsources, and show that the recurrent layers enable the spatial tracking of\nmoving sources when trained with dynamic scenes. The tracking performance of\nthe CRNN is compared with a stand-alone tracking method that combines a\nmulti-source (DOA) estimator and a particle filter. Their respective\nperformance is evaluated in various acoustic conditions such as anechoic and\nreverberant scenarios, stationary and moving sources at several angular\nvelocities, and with a varying number of overlapping sources. The results show\nthat the CRNN manages to track multiple sources more consistently than the\nparametric method across acoustic scenarios, but at the cost of higher\nlocalization error.","url_abs":"http://arxiv.org/abs/1904.12769v1","url_pdf":"http://arxiv.org/pdf/1904.12769v1.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":"localization-detection-and-tracking-of","repo_url":"https://github.com/sharathadavanne/seld-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}