{"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/mmdenselstm-an-efficient-combination-of","title":"MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation","arxiv_id":"1805.02410","date":"2018-05-07","proceeding":null,"authors":["Naoya Takahashi","Nabarun Goswami","Yuki Mitsufuji"],"abstract":"Deep neural networks have become an indispensable technique for audio source separation (ASS). It was recently reported that a variant of CNN architecture called MMDenseNet was successfully employed to solve the ASS problem of estimating source amplitudes, and state-of-the-art results were obtained for DSD100 dataset. To further enhance MMDenseNet, here we propose a novel architecture that integrates long short-term memory (LSTM) in multiple scales with skip connections to efficiently model long-term structures within an audio context. The experimental results show that the proposed method outperforms MMDenseNet, LSTM and a blend of the two networks. The number of parameters and processing time of the proposed model are significantly less than those for simple blending. Furthermore, the proposed method yields better results than those obtained using ideal binary masks for a singing voice separation task.","url_abs":"https://arxiv.org/abs/1805.02410v2","url_pdf":"https://arxiv.org/pdf/1805.02410v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"mmdenselstm-an-efficient-combination-of","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"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/music-source-separation-on-musdb18","task":"Music Source Separation","dataset":"MUSDB18","model":"TAK2","rank_in_archive_order":17,"of":27,"metrics":{"SDR (avg)":"6.04","SDR (bass)":"5.40","SDR (drums)":"6.81","SDR (other)":"4.80","SDR (vocals)":"7.16"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.02410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.02410"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tsurumeso/vocal-remover","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2c5f4f581b03c006","entry":"crop_center","repo":"tsurumeso/vocal-remover","repo_kind":"listed","path":"lib/spec_utils.py","file_url":"https://github.com/tsurumeso/vocal-remover/blob/HEAD/lib/spec_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c5f4f581b03c006"}},{"code_sha256_prefix":"a449633d34833f2d","entry":"imread","repo":"tsurumeso/vocal-remover","repo_kind":"listed","path":"lib/utils.py","file_url":"https://github.com/tsurumeso/vocal-remover/blob/HEAD/lib/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a449633d34833f2d"}},{"code_sha256_prefix":"f8a66396c25cb91a","entry":"imwrite","repo":"tsurumeso/vocal-remover","repo_kind":"listed","path":"lib/utils.py","file_url":"https://github.com/tsurumeso/vocal-remover/blob/HEAD/lib/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8a66396c25cb91a"}},{"code_sha256_prefix":"819d810e0d2493b0","entry":"make_padding","repo":"tsurumeso/vocal-remover","repo_kind":"listed","path":"lib/dataset.py","file_url":"https://github.com/tsurumeso/vocal-remover/blob/HEAD/lib/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"819d810e0d2493b0"}},{"code_sha256_prefix":"be42da4ca7a9e660","entry":"make_pair","repo":"tsurumeso/vocal-remover","repo_kind":"listed","path":"lib/dataset.py","file_url":"https://github.com/tsurumeso/vocal-remover/blob/HEAD/lib/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be42da4ca7a9e660"}},{"code_sha256_prefix":"86e0f8102366a48b","entry":"spectrogram_to_image","repo":"tsurumeso/vocal-remover","repo_kind":"listed","path":"lib/spec_utils.py","file_url":"https://github.com/tsurumeso/vocal-remover/blob/HEAD/lib/spec_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86e0f8102366a48b"}},{"code_sha256_prefix":"8f3394212ec277e8","entry":"train_val_split","repo":"tsurumeso/vocal-remover","repo_kind":"listed","path":"lib/dataset.py","file_url":"https://github.com/tsurumeso/vocal-remover/blob/HEAD/lib/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f3394212ec277e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}