{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YUDJJRK7ML3Q4Y3TIYJW3C43Z3","short_pith_number":"pith:YUDJJRK7","schema_version":"1.0","canonical_sha256":"c50694c55f62f70e637346136d8b9bceede63e03517acea73044133a12839c12","source":{"kind":"arxiv","id":"1807.00129","version":3},"attestation_state":"computed","paper":{"title":"Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Archontis Politis, Joonas Nikunen, Sharath Adavanne, Tuomas Virtanen","submitted_at":"2018-06-30T06:05:20Z","abstract_excerpt":"In this paper, we propose a convolutional recurrent neural network for joint sound event localization and detection (SELD) of multiple overlapping sound events in three-dimensional (3D) space. The proposed network takes a sequence of consecutive spectrogram time-frames as input and maps it to two outputs in parallel. As the first output, the sound event detection (SED) is performed as a multi-label classification task on each time-frame producing temporal activity for all the sound event classes. As the second output, localization is performed by estimating the 3D Cartesian coordinates of the "},"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":"1807.00129","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2018-06-30T06:05:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"32896faeac94a4a3f84b651417af62de650c78d602390cbb46eecdb305b9889e","abstract_canon_sha256":"9faf1cc5e475ab8ac950d9042a17888629b730577cfeafa07a49271a3cdce68f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:14.141282Z","signature_b64":"WXp8zNPKmxevFoU6krNbODyCQ+a8j4ZA0slueRY4JzGymWPVOacD6qAlV2DReaqphW3v1pCwVLFD7sXNvaP/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c50694c55f62f70e637346136d8b9bceede63e03517acea73044133a12839c12","last_reissued_at":"2026-05-17T23:58:14.140741Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:14.140741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Archontis Politis, Joonas Nikunen, Sharath Adavanne, Tuomas Virtanen","submitted_at":"2018-06-30T06:05:20Z","abstract_excerpt":"In this paper, we propose a convolutional recurrent neural network for joint sound event localization and detection (SELD) of multiple overlapping sound events in three-dimensional (3D) space. The proposed network takes a sequence of consecutive spectrogram time-frames as input and maps it to two outputs in parallel. As the first output, the sound event detection (SED) is performed as a multi-label classification task on each time-frame producing temporal activity for all the sound event classes. As the second output, localization is performed by estimating the 3D Cartesian coordinates of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00129","kind":"arxiv","version":3},"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":"1807.00129","created_at":"2026-05-17T23:58:14.140818+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00129v3","created_at":"2026-05-17T23:58:14.140818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00129","created_at":"2026-05-17T23:58:14.140818+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUDJJRK7ML3Q","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUDJJRK7ML3Q4Y3T","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUDJJRK7","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.02296","citing_title":"Spatial Speech Perception Systems: A Survey of Sound Source Localization, Directional Enhancement, and Speech Recognition","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3","json":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3.json","graph_json":"https://pith.science/api/pith-number/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/graph.json","events_json":"https://pith.science/api/pith-number/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/events.json","paper":"https://pith.science/paper/YUDJJRK7"},"agent_actions":{"view_html":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3","download_json":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3.json","view_paper":"https://pith.science/paper/YUDJJRK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00129&json=true","fetch_graph":"https://pith.science/api/pith-number/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/graph.json","fetch_events":"https://pith.science/api/pith-number/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/action/storage_attestation","attest_author":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/action/author_attestation","sign_citation":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/action/citation_signature","submit_replication":"https://pith.science/pith/YUDJJRK7ML3Q4Y3TIYJW3C43Z3/action/replication_record"}},"created_at":"2026-05-17T23:58:14.140818+00:00","updated_at":"2026-05-17T23:58:14.140818+00:00"}