{"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/a-closer-look-at-weak-label-learning-for","title":"A Closer Look at Weak Label Learning for Audio Events","arxiv_id":"1804.09288","date":"2018-04-24","proceeding":null,"authors":["Ankit Shah","Anurag Kumar","Alexander G. Hauptmann","Bhiksha Raj"],"abstract":"Audio content analysis in terms of sound events is an important research\nproblem for a variety of applications. Recently, the development of weak\nlabeling approaches for audio or sound event detection (AED) and availability\nof large scale weakly labeled dataset have finally opened up the possibility of\nlarge scale AED. However, a deeper understanding of how weak labels affect the\nlearning for sound events is still missing from literature. In this work, we\nfirst describe a CNN based approach for weakly supervised training of audio\nevents. The approach follows some basic design principle desirable in a\nlearning method relying on weakly labeled audio. We then describe important\ncharacteristics, which naturally arise in weakly supervised learning of sound\nevents. We show how these aspects of weak labels affect the generalization of\nmodels. More specifically, we study how characteristics such as label density\nand corruption of labels affects weakly supervised training for audio events.\nWe also study the feasibility of directly obtaining weak labeled data from the\nweb without any manual label and compare it with a dataset which has been\nmanually labeled. The analysis and understanding of these factors should be\ntaken into picture in the development of future weak label learning methods.\nAudioset, a large scale weakly labeled dataset for sound events is used in our\nexperiments.","url_abs":"http://arxiv.org/abs/1804.09288v1","url_pdf":"http://arxiv.org/pdf/1804.09288v1.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":"a-closer-look-at-weak-label-learning-for","repo_url":"https://github.com/ankitshah009/WALNet-Weak_Label_Analysis","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"sound-event-detection","task_name":"Sound Event Detection"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.09288","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}