{"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/recurrent-neural-networks-with-stochastic","title":"Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection","arxiv_id":"1902.04980","date":"2019-02-13","proceeding":null,"authors":["Duong Nguyen","Oliver S. Kirsebom","Fábio Frazão","Ronan Fablet","Stan Matwin"],"abstract":"In this paper, we adapt Recurrent Neural Networks with Stochastic Layers,\nwhich are the state-of-the-art for generating text, music and speech, to the\nproblem of acoustic novelty detection. By integrating uncertainty into the\nhidden states, this type of network is able to learn the distribution of\ncomplex sequences. Because the learned distribution can be calculated\nexplicitly in terms of probability, we can evaluate how likely an observation\nis then detect low-probability events as novel. The model is robust, highly\nunsupervised, end-to-end and requires minimum preprocessing, feature\nengineering or hyperparameter tuning. An experiment on a benchmark dataset\nshows that our model outperforms the state-of-the-art acoustic novelty\ndetectors.","url_abs":"http://arxiv.org/abs/1902.04980v1","url_pdf":"http://arxiv.org/pdf/1902.04980v1.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":"recurrent-neural-networks-with-stochastic","repo_url":"https://github.com/dnguyengithub/AudioNovelty","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"acoustic-novelty-detection","task_name":"Acoustic Novelty Detection"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"novelty-detection","task_name":"Novelty Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/acoustic-novelty-detection-on-a3lab-pascal","task":"Acoustic Novelty Detection","dataset":"A3Lab PASCAL CHiME","model":"VRNN","rank_in_archive_order":2,"of":3,"metrics":{"F1":"93.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}