{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MJPXT5KHLLAM7U57ZBN3SY4K4I","short_pith_number":"pith:MJPXT5KH","schema_version":"1.0","canonical_sha256":"625f79f5475ac0cfd3bfc85bb9638ae21f1459494016f7342a7600dfa4c032d5","source":{"kind":"arxiv","id":"1805.02410","version":2},"attestation_state":"computed","paper":{"title":"MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Nabarun Goswami, Naoya Takahashi, Yuki Mitsufuji","submitted_at":"2018-05-07T09:18:25Z","abstract_excerpt":"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 out"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1805.02410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-05-07T09:18:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"880d7e4f6ec222075d297de47ff92e131fe23accaed780a939801cc44c877d4b","abstract_canon_sha256":"5e9c87c0aff0adacb3077c4f4785d554dce6417b248fd78452fd9f3cef859f4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:43.956720Z","signature_b64":"OAxr1Bwcw6/duWMMEMnWfB04uYnJIjEULpC1egiGiwT9qfBTdY82E9vVhk4gBLzUmn5pw7f3vrW2KN7kZESCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"625f79f5475ac0cfd3bfc85bb9638ae21f1459494016f7342a7600dfa4c032d5","last_reissued_at":"2026-05-18T00:14:43.956324Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:43.956324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Nabarun Goswami, Naoya Takahashi, Yuki Mitsufuji","submitted_at":"2018-05-07T09:18:25Z","abstract_excerpt":"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 out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.02410","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1805.02410","created_at":"2026-05-18T00:14:43.956381+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.02410v2","created_at":"2026-05-18T00:14:43.956381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.02410","created_at":"2026-05-18T00:14:43.956381+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJPXT5KHLLAM","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJPXT5KHLLAM7U57","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJPXT5KH","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01174","citing_title":"Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I","json":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I.json","graph_json":"https://pith.science/api/pith-number/MJPXT5KHLLAM7U57ZBN3SY4K4I/graph.json","events_json":"https://pith.science/api/pith-number/MJPXT5KHLLAM7U57ZBN3SY4K4I/events.json","paper":"https://pith.science/paper/MJPXT5KH"},"agent_actions":{"view_html":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I","download_json":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I.json","view_paper":"https://pith.science/paper/MJPXT5KH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.02410&json=true","fetch_graph":"https://pith.science/api/pith-number/MJPXT5KHLLAM7U57ZBN3SY4K4I/graph.json","fetch_events":"https://pith.science/api/pith-number/MJPXT5KHLLAM7U57ZBN3SY4K4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I/action/storage_attestation","attest_author":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I/action/author_attestation","sign_citation":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I/action/citation_signature","submit_replication":"https://pith.science/pith/MJPXT5KHLLAM7U57ZBN3SY4K4I/action/replication_record"}},"created_at":"2026-05-18T00:14:43.956381+00:00","updated_at":"2026-05-18T00:14:43.956381+00:00"}