{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ALN2OQHO5NFCKA5LQN2GPS5BN2","short_pith_number":"pith:ALN2OQHO","schema_version":"1.0","canonical_sha256":"02dba740eeeb4a2503ab837467cba16ea40610db681a2cb313290b3702c34c02","source":{"kind":"arxiv","id":"2106.06969","version":2},"attestation_state":"computed","paper":{"title":"SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrew Markham, Niki Trigoni, Yuhang He","submitted_at":"2021-06-13T11:43:41Z","abstract_excerpt":"We present a new framework SoundDet, which is an end-to-end trainable and light-weight framework, for polyphonic moving sound event detection and localization. Prior methods typically approach this problem by preprocessing raw waveform into time-frequency representations, which is more amenable to process with well-established image processing pipelines. Prior methods also detect in segment-wise manner, leading to incomplete and partial detections. SoundDet takes a novel approach and directly consumes the raw, multichannel waveform and treats the spatio-temporal sound event as a complete \"soun"},"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":"2106.06969","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-13T11:43:41Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"8953b977410266d748b3ab84a2bdb5784b48e88a683d6b5df0a9c37b1a1f2cb7","abstract_canon_sha256":"a8acf2d7c99325367abb93074dd242d3fb188cbd8700e95bbf464cc2601f9b8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:49.833935Z","signature_b64":"yUkXjAhlQMpZ+1VSGzcsb08TWGEJN9xFImrwC1LxydAQtZf1SOL8DCPl4yOqbn/uqfcRBxiGhZLKQ/QMAj8pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02dba740eeeb4a2503ab837467cba16ea40610db681a2cb313290b3702c34c02","last_reissued_at":"2026-07-05T03:07:49.833546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:49.833546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrew Markham, Niki Trigoni, Yuhang He","submitted_at":"2021-06-13T11:43:41Z","abstract_excerpt":"We present a new framework SoundDet, which is an end-to-end trainable and light-weight framework, for polyphonic moving sound event detection and localization. Prior methods typically approach this problem by preprocessing raw waveform into time-frequency representations, which is more amenable to process with well-established image processing pipelines. Prior methods also detect in segment-wise manner, leading to incomplete and partial detections. SoundDet takes a novel approach and directly consumes the raw, multichannel waveform and treats the spatio-temporal sound event as a complete \"soun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06969","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.06969/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":"2106.06969","created_at":"2026-07-05T03:07:49.833603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06969v2","created_at":"2026-07-05T03:07:49.833603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06969","created_at":"2026-07-05T03:07:49.833603+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALN2OQHO5NFC","created_at":"2026-07-05T03:07:49.833603+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALN2OQHO5NFCKA5L","created_at":"2026-07-05T03:07:49.833603+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALN2OQHO","created_at":"2026-07-05T03:07:49.833603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27751","citing_title":"From General-Purpose Audio Tagging to Spatially Grounded Sound Event Localization and Detection","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2","json":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2.json","graph_json":"https://pith.science/api/pith-number/ALN2OQHO5NFCKA5LQN2GPS5BN2/graph.json","events_json":"https://pith.science/api/pith-number/ALN2OQHO5NFCKA5LQN2GPS5BN2/events.json","paper":"https://pith.science/paper/ALN2OQHO"},"agent_actions":{"view_html":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2","download_json":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2.json","view_paper":"https://pith.science/paper/ALN2OQHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06969&json=true","fetch_graph":"https://pith.science/api/pith-number/ALN2OQHO5NFCKA5LQN2GPS5BN2/graph.json","fetch_events":"https://pith.science/api/pith-number/ALN2OQHO5NFCKA5LQN2GPS5BN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2/action/storage_attestation","attest_author":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2/action/author_attestation","sign_citation":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2/action/citation_signature","submit_replication":"https://pith.science/pith/ALN2OQHO5NFCKA5LQN2GPS5BN2/action/replication_record"}},"created_at":"2026-07-05T03:07:49.833603+00:00","updated_at":"2026-07-05T03:07:49.833603+00:00"}