{"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/masked-conditional-neural-networks-for-1","title":"Masked Conditional Neural Networks for Environmental Sound Classification","arxiv_id":"1805.10004","date":"2018-05-25","proceeding":null,"authors":["Fady Medhat","David Chesmore","John Robinson"],"abstract":"The ConditionaL Neural Network (CLNN) exploits the nature of the temporal\nsequencing of the sound signal represented in a spectrogram, and its variant\nthe Masked ConditionaL Neural Network (MCLNN) induces the network to learn in\nfrequency bands by embedding a filterbank-like sparseness over the network's\nlinks using a binary mask. Additionally, the masking automates the exploration\nof different feature combinations concurrently analogous to handcrafting the\noptimum combination of features for a recognition task. We have evaluated the\nMCLNN performance using the Urbansound8k dataset of environmental sounds.\nAdditionally, we present a collection of manually recorded sounds for rail and\nroad traffic, YorNoise, to investigate the confusion rates among machine\ngenerated sounds possessing low-frequency components. MCLNN has achieved\ncompetitive results without augmentation and using 12% of the trainable\nparameters utilized by an equivalent model based on state-of-the-art\nConvolutional Neural Networks on the Urbansound8k. We extended the Urbansound8k\ndataset with YorNoise, where experiments have shown that common tonal\nproperties affect the classification performance.","url_abs":"http://arxiv.org/abs/1805.10004v2","url_pdf":"http://arxiv.org/pdf/1805.10004v2.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":"masked-conditional-neural-networks-for-1","repo_url":"https://github.com/fadymedhat/MCLNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"masked-conditional-neural-networks-for-1","repo_url":"https://github.com/fadymedhat/YorNoise","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"environmental-sound-classification","task_name":"Environmental Sound Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sound-classification","task_name":"Sound Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}