{"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/multi-scale-multi-band-densenets-for-audio","title":"Multi-scale Multi-band DenseNets for Audio Source Separation","arxiv_id":"1706.09588","date":"2017-06-29","proceeding":null,"authors":["Naoya Takahashi","Yuki Mitsufuji"],"abstract":"This paper deals with the problem of audio source separation. To handle the\ncomplex and ill-posed nature of the problems of audio source separation, the\ncurrent state-of-the-art approaches employ deep neural networks to obtain\ninstrumental spectra from a mixture. In this study, we propose a novel network\narchitecture that extends the recently developed densely connected\nconvolutional network (DenseNet), which has shown excellent results on image\nclassification tasks. To deal with the specific problem of audio source\nseparation, an up-sampling layer, block skip connection and band-dedicated\ndense blocks are incorporated on top of DenseNet. The proposed approach takes\nadvantage of long contextual information and outperforms state-of-the-art\nresults on SiSEC 2016 competition by a large margin in terms of\nsignal-to-distortion ratio. Moreover, the proposed architecture requires\nsignificantly fewer parameters and considerably less training time compared\nwith other methods.","url_abs":"http://arxiv.org/abs/1706.09588v1","url_pdf":"http://arxiv.org/pdf/1706.09588v1.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":"multi-scale-multi-band-densenets-for-audio","repo_url":"https://github.com/Anjok07/ultimatevocalremovergui","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-scale-multi-band-densenets-for-audio","repo_url":"https://github.com/siximumushui/vocalremover","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-scale-multi-band-densenets-for-audio","repo_url":"https://github.com/tsurumeso/vocal-remover","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-scale-multi-band-densenets-for-audio","repo_url":"https://github.com/2023-MindSpore-4/Code2/tree/main/3D_DenseNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"multi-scale-multi-band-densenets-for-audio","repo_url":"https://github.com/code-implementation1/Code9/tree/main/densenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"audio-source-separation","task_name":"Audio Source Separation"},{"task_slug":"music-source-separation","task_name":"Music Source Separation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.09588","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}