{"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/robust-audio-event-recognition-with-1-max","title":"Robust Audio Event Recognition with 1-Max Pooling Convolutional Neural Networks","arxiv_id":"1604.06338","date":"2016-04-21","proceeding":null,"authors":["Huy Phan","Lars Hertel","Marco Maass","Alfred Mertins"],"abstract":"We present in this paper a simple, yet efficient convolutional neural network\n(CNN) architecture for robust audio event recognition. Opposing to deep CNN\narchitectures with multiple convolutional and pooling layers topped up with\nmultiple fully connected layers, the proposed network consists of only three\nlayers: convolutional, pooling, and softmax layer. Two further features\ndistinguish it from the deep architectures that have been proposed for the\ntask: varying-size convolutional filters at the convolutional layer and 1-max\npooling scheme at the pooling layer. In intuition, the network tends to select\nthe most discriminative features from the whole audio signals for recognition.\nOur proposed CNN not only shows state-of-the-art performance on the standard\ntask of robust audio event recognition but also outperforms other deep\narchitectures up to 4.5% in terms of recognition accuracy, which is equivalent\nto 76.3% relative error reduction.","url_abs":"http://arxiv.org/abs/1604.06338v2","url_pdf":"http://arxiv.org/pdf/1604.06338v2.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":"robust-audio-event-recognition-with-1-max","repo_url":"https://github.com/9552nZ/SmartSheetMusic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}