{"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-perceptually-motivated-approach-for-low-1","title":"A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech","arxiv_id":"2008.04259","date":"2020-08-27","proceeding":"Interspeech 2020 8","authors":[],"abstract":"Over the past few years, speech enhancement methods based on deep learning\nhave greatly surpassed traditional methods based on spectral subtraction and\nspectral estimation. Many of these new techniques operate directly in the the\nshort-time Fourier transform (STFT) domain, resulting in a high computational\ncomplexity. In this work, we propose PercepNet, an efficient approach that\nrelies on human perception of speech by focusing on the spectral envelope and\non the periodicity of the speech. We demonstrate high-quality, real-time\nenhancement of fullband (48 kHz) speech with less than 5% of a CPU core.","url_abs":"http://arxiv.org/abs/2008.04259v2","url_pdf":"http://arxiv.org/pdf/2008.04259v2.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-perceptually-motivated-approach-for-low-1","repo_url":"https://github.com/jzi040941/PercepNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-perceptually-motivated-approach-for-low-1","repo_url":"https://github.com/cookcodes/percepnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}