{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZPY4243Z52LUFLJYMZVGYG56B2","short_pith_number":"pith:ZPY4243Z","schema_version":"1.0","canonical_sha256":"cbf1cd7379ee9742ad38666a6c1bbe0e80657f471e6469cda4f6e6a0699fc786","source":{"kind":"arxiv","id":"1801.09522","version":1},"attestation_state":"computed","paper":{"title":"Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Archontis Politis, Sharath Adavanne, Tuomas Virtanen","submitted_at":"2018-01-29T14:24:39Z","abstract_excerpt":"In this paper, we propose a stacked convolutional and recurrent neural network (CRNN) with a 3D convolutional neural network (CNN) in the first layer for the multichannel sound event detection (SED) task. The 3D CNN enables the network to simultaneously learn the inter- and intra-channel features from the input multichannel audio. In order to evaluate the proposed method, multichannel audio datasets with different number of overlapping sound sources are synthesized. Each of this dataset has a four-channel first-order Ambisonic, binaural, and single-channel versions, on which the performance of"},"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":"1801.09522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2018-01-29T14:24:39Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"b3c8723261ecbc39fa6f0a6587bf9efe8762424ca67d01bc1a7db806ff66adcf","abstract_canon_sha256":"d8c63445c6a618e5fe5c5913d6be4eee06b740ad321aafa045e1d5a2aad282d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:57.157991Z","signature_b64":"lySl7nLAJV0KCLX/p4TFrHR1ZE+AYurWXhawfaBYgs+x2n9yvS7zk8n0I9eb1QnRaAmw0YFx2lD28aD5TqjtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbf1cd7379ee9742ad38666a6c1bbe0e80657f471e6469cda4f6e6a0699fc786","last_reissued_at":"2026-05-18T00:24:57.157361Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:57.157361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Archontis Politis, Sharath Adavanne, Tuomas Virtanen","submitted_at":"2018-01-29T14:24:39Z","abstract_excerpt":"In this paper, we propose a stacked convolutional and recurrent neural network (CRNN) with a 3D convolutional neural network (CNN) in the first layer for the multichannel sound event detection (SED) task. The 3D CNN enables the network to simultaneously learn the inter- and intra-channel features from the input multichannel audio. In order to evaluate the proposed method, multichannel audio datasets with different number of overlapping sound sources are synthesized. Each of this dataset has a four-channel first-order Ambisonic, binaural, and single-channel versions, on which the performance of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09522","kind":"arxiv","version":1},"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":"1801.09522","created_at":"2026-05-18T00:24:57.157459+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.09522v1","created_at":"2026-05-18T00:24:57.157459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09522","created_at":"2026-05-18T00:24:57.157459+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPY4243Z52LU","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPY4243Z52LUFLJY","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPY4243Z","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2","json":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2.json","graph_json":"https://pith.science/api/pith-number/ZPY4243Z52LUFLJYMZVGYG56B2/graph.json","events_json":"https://pith.science/api/pith-number/ZPY4243Z52LUFLJYMZVGYG56B2/events.json","paper":"https://pith.science/paper/ZPY4243Z"},"agent_actions":{"view_html":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2","download_json":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2.json","view_paper":"https://pith.science/paper/ZPY4243Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.09522&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPY4243Z52LUFLJYMZVGYG56B2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPY4243Z52LUFLJYMZVGYG56B2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2/action/storage_attestation","attest_author":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2/action/author_attestation","sign_citation":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2/action/citation_signature","submit_replication":"https://pith.science/pith/ZPY4243Z52LUFLJYMZVGYG56B2/action/replication_record"}},"created_at":"2026-05-18T00:24:57.157459+00:00","updated_at":"2026-05-18T00:24:57.157459+00:00"}