{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QHBY4IR2BHBGGVWLIXICVIOFQF","short_pith_number":"pith:QHBY4IR2","schema_version":"1.0","canonical_sha256":"81c38e223a09c26356cb45d02aa1c5814eca4626d99120d8ca548ca26f7bfd7b","source":{"kind":"arxiv","id":"2110.00275","version":3},"attestation_state":"computed","paper":{"title":"SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Douglas L. Jones, Karn N. Watcharasupat, Ngoc Khanh Nguyen, Thi Ngoc Tho Nguyen, Woon-Seng Gan","submitted_at":"2021-10-01T09:01:35Z","abstract_excerpt":"Sound event localization and detection (SELD) consists of two subtasks, which are sound event detection and direction-of-arrival estimation. While sound event detection mainly relies on time-frequency patterns to distinguish different sound classes, direction-of-arrival estimation uses amplitude and/or phase differences between microphones to estimate source directions. As a result, it is often difficult to jointly optimize these two subtasks. We propose a novel feature called Spatial cue-Augmented Log-SpectrogrAm (SALSA) with exact time-frequency mapping between the signal power and the sourc"},"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":"2110.00275","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-01T09:01:35Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c327984d189101834987755f70ff629a65c838e15bd42451a8c1eab4ee7f9828","abstract_canon_sha256":"f3975fe180f08ed61d77e82ff65995e4939d177d430b510631d2d72d7fcd87f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:09.621673Z","signature_b64":"VOAgeioGog096Hj9eEsDXoHnvflue9G+/ruNbdqOPrry6nzsqX1kOdbjd1XueFHK7ZQhDICWn4+ZCcpsq5tWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81c38e223a09c26356cb45d02aa1c5814eca4626d99120d8ca548ca26f7bfd7b","last_reissued_at":"2026-07-05T04:29:09.621156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:09.621156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Douglas L. Jones, Karn N. Watcharasupat, Ngoc Khanh Nguyen, Thi Ngoc Tho Nguyen, Woon-Seng Gan","submitted_at":"2021-10-01T09:01:35Z","abstract_excerpt":"Sound event localization and detection (SELD) consists of two subtasks, which are sound event detection and direction-of-arrival estimation. While sound event detection mainly relies on time-frequency patterns to distinguish different sound classes, direction-of-arrival estimation uses amplitude and/or phase differences between microphones to estimate source directions. As a result, it is often difficult to jointly optimize these two subtasks. We propose a novel feature called Spatial cue-Augmented Log-SpectrogrAm (SALSA) with exact time-frequency mapping between the signal power and the sourc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00275","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.00275/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.00275","created_at":"2026-07-05T04:29:09.621216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.00275v3","created_at":"2026-07-05T04:29:09.621216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00275","created_at":"2026-07-05T04:29:09.621216+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHBY4IR2BHBG","created_at":"2026-07-05T04:29:09.621216+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHBY4IR2BHBGGVWL","created_at":"2026-07-05T04:29:09.621216+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHBY4IR2","created_at":"2026-07-05T04:29:09.621216+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/QHBY4IR2BHBGGVWLIXICVIOFQF","json":"https://pith.science/pith/QHBY4IR2BHBGGVWLIXICVIOFQF.json","graph_json":"https://pith.science/api/pith-number/QHBY4IR2BHBGGVWLIXICVIOFQF/graph.json","events_json":"https://pith.science/api/pith-number/QHBY4IR2BHBGGVWLIXICVIOFQF/events.json","paper":"https://pith.science/paper/QHBY4IR2"},"agent_actions":{"view_html":"https://pith.science/pith/QHBY4IR2BHBGGVWLIXICVIOFQF","download_json":"https://pith.science/pith/QHBY4IR2BHBGGVWLIXICVIOFQF.json","view_paper":"https://pith.science/paper/QHBY4IR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.00275&json=true","fetch_graph":"https://pith.science/api/pith-number/QHBY4IR2BHBGGVWLIXICVIOFQF/graph.json","fetch_events":"https://pith.science/api/pith-number/QHBY4IR2BHBGGVWLIXICVIOFQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHBY4IR2BHBGGVWLIXICVIOFQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHBY4IR2BHBGGVWLIXICVIOFQF/action/storage_attestation","attest_author":"https://pith.science/pith/QHBY4IR2BHBGGVWLIXICVIOFQF/action/author_attestation","sign_citation":"https://pith.science/pith/QHBY4IR2BHBGGVWLIXICVIOFQF/action/citation_signature","submit_replication":"https://pith.science/pith/QHBY4IR2BHBGGVWLIXICVIOFQF/action/replication_record"}},"created_at":"2026-07-05T04:29:09.621216+00:00","updated_at":"2026-07-05T04:29:09.621216+00:00"}