{"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/kuielab-mdx-net-a-two-stream-neural-network","title":"KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing","arxiv_id":"2111.12203","date":"2021-11-24","proceeding":null,"authors":["Minseok Kim","Woosung Choi","Jaehwa Chung","Daewon Lee","Soonyoung Jung"],"abstract":"Recently, many methods based on deep learning have been proposed for music source separation. Some state-of-the-art methods have shown that stacking many layers with many skip connections improve the SDR performance. Although such a deep and complex architecture shows outstanding performance, it usually requires numerous computing resources and time for training and evaluation. This paper proposes a two-stream neural network for music demixing, called KUIELab-MDX-Net, which shows a good balance of performance and required resources. The proposed model has a time-frequency branch and a time-domain branch, where each branch separates stems, respectively. It blends results from two streams to generate the final estimation. KUIELab-MDX-Net took second place on leaderboard A and third place on leaderboard B in the Music Demixing Challenge at ISMIR 2021. This paper also summarizes experimental results on another benchmark, MUSDB18. Our source code is available online.","url_abs":"https://arxiv.org/abs/2111.12203v1","url_pdf":"https://arxiv.org/pdf/2111.12203v1.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":"kuielab-mdx-net-a-two-stream-neural-network","repo_url":"https://github.com/kuielab/mdx-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"music-source-separation","task_name":"Music Source Separation"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/music-source-separation-on-musdb18","task":"Music Source Separation","dataset":"MUSDB18","model":"KUIELab-MDX-Net","rank_in_archive_order":7,"of":27,"metrics":{"SDR (avg)":"7.54","SDR (bass)":"7.86","SDR (drums)":"7.33","SDR (other)":"5.95","SDR (vocals)":"9.00"},"uses_additional_data":false},{"leaderboard":"/sota/music-source-separation-on-musdb18-hq","task":"Music Source Separation","dataset":"MUSDB18-HQ","model":"KUIELab-MDX-Net","rank_in_archive_order":12,"of":14,"metrics":{"SDR (avg)":"7.47","SDR (bass)":"7.83","SDR (drums)":"7.20","SDR (others)":"5.90","SDR (vocals)":"8.97"},"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}