{"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/spectrogram-channels-u-net-a-source","title":"Spectrogram-channels u-net: a source separation model viewing each channel as the spectrogram of each source","arxiv_id":"1810.11520","date":"2018-10-26","proceeding":null,"authors":["Jaehoon Oh","Duyeon Kim","Se-Young Yun"],"abstract":"Sound source separation has attracted attention from Music Information\nRetrieval(MIR) researchers, since it is related to many MIR tasks such as\nautomatic lyric transcription, singer identification, and voice conversion. In\nthis paper, we propose an intuitive spectrogram-based model for source\nseparation by adapting U-Net. We call it Spectrogram-Channels U-Net, which\nmeans each channel of the output corresponds to the spectrogram of separated\nsource itself. The proposed model can be used for not only singing voice\nseparation but also multi-instrument separation by changing only the number of\noutput channels. In addition, we propose a loss function that balances volumes\nbetween different sources. Finally, we yield performance that is\nstate-of-the-art on both separation tasks.","url_abs":"http://arxiv.org/abs/1810.11520v2","url_pdf":"http://arxiv.org/pdf/1810.11520v2.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":"spectrogram-channels-u-net-a-source","repo_url":"https://github.com/lucas-dunker/stem-separator-amt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"music-information-retrieval","task_name":"Music Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"singer-identification","task_name":"Singer Identification"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}