{"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/improving-dnn-based-music-source-separation","title":"Improving DNN-based Music Source Separation using Phase Features","arxiv_id":"1807.02710","date":"2018-07-07","proceeding":null,"authors":["Joachim Muth","Stefan Uhlich","Nathanael Perraudin","Thomas Kemp","Fabien Cardinaux","Yuki Mitsufuji"],"abstract":"Music source separation with deep neural networks typically relies only on\namplitude features. In this paper we show that additional phase features can\nimprove the separation performance. Using the theoretical relationship between\nSTFT phase and amplitude, we conjecture that derivatives of the phase are a\ngood feature representation opposed to the raw phase. We verify this conjecture\nexperimentally and propose a new DNN architecture which combines amplitude and\nphase. This joint approach achieves a better signal-to distortion ratio on the\nDSD100 dataset for all instruments compared to a network that uses only\namplitude features. Especially, the bass instrument benefits from the phase\ninformation.","url_abs":"http://arxiv.org/abs/1807.02710v3","url_pdf":"http://arxiv.org/pdf/1807.02710v3.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":"improving-dnn-based-music-source-separation","repo_url":"https://github.com/aRI0U/music-source-separation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"music-source-separation","task_name":"Music Source Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}