{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PCBUXUOUOK4XBGY7BOBTVKL5IO","short_pith_number":"pith:PCBUXUOU","schema_version":"1.0","canonical_sha256":"78834bd1d472b9709b1f0b833aa97d43a8d552acf08d7cb4bf3e4993b38fec44","source":{"kind":"arxiv","id":"2304.12688","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Audio-Tagging Assisted Sound Event Detection using Weakified Strong Labels and Frequency Dynamic Convolutions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andrew Koh, Eng Siong Chng, Rohan Kumar Das, Tanmay Khandelwal","submitted_at":"2023-04-25T09:43:40Z","abstract_excerpt":"Jointly learning from a small labeled set and a larger unlabeled set is an active research topic under semi-supervised learning (SSL). In this paper, we propose a novel SSL method based on a two-stage framework for leveraging a large unlabeled in-domain set. Stage-1 of our proposed framework focuses on audio-tagging (AT), which assists the sound event detection (SED) system in Stage-2. The AT system is trained utilizing a strongly labeled set converted into weak predictions referred to as weakified set, a weakly labeled set, and an unlabeled set. This AT system then infers on the unlabeled set"},"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":"2304.12688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-25T09:43:40Z","cross_cats_sorted":[],"title_canon_sha256":"7643b58b398690e1f36b42d20a8a20361f6e2b40af6fd0108b651101b8fe8557","abstract_canon_sha256":"f384a3595499802bd53d553019d8f296ec3b15927e81e1508253abdfa4acc7a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:19.815698Z","signature_b64":"VTaKGZh3SggZW3pnn1edoc3xgPBlaMc0NWLJXpY1H6+yJdW+kaR2rxX75Zir+pBih6AJ8ipg4fXcYUWRuVWOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78834bd1d472b9709b1f0b833aa97d43a8d552acf08d7cb4bf3e4993b38fec44","last_reissued_at":"2026-07-05T06:04:19.815190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:19.815190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Audio-Tagging Assisted Sound Event Detection using Weakified Strong Labels and Frequency Dynamic Convolutions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andrew Koh, Eng Siong Chng, Rohan Kumar Das, Tanmay Khandelwal","submitted_at":"2023-04-25T09:43:40Z","abstract_excerpt":"Jointly learning from a small labeled set and a larger unlabeled set is an active research topic under semi-supervised learning (SSL). In this paper, we propose a novel SSL method based on a two-stage framework for leveraging a large unlabeled in-domain set. Stage-1 of our proposed framework focuses on audio-tagging (AT), which assists the sound event detection (SED) system in Stage-2. The AT system is trained utilizing a strongly labeled set converted into weak predictions referred to as weakified set, a weakly labeled set, and an unlabeled set. This AT system then infers on the unlabeled set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12688","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.12688/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":"2304.12688","created_at":"2026-07-05T06:04:19.815244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12688v1","created_at":"2026-07-05T06:04:19.815244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12688","created_at":"2026-07-05T06:04:19.815244+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCBUXUOUOK4X","created_at":"2026-07-05T06:04:19.815244+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCBUXUOUOK4XBGY7","created_at":"2026-07-05T06:04:19.815244+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCBUXUOU","created_at":"2026-07-05T06:04:19.815244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12785","citing_title":"Frequency Dynamic Convolutions for Sound Event Detection","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO","json":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO.json","graph_json":"https://pith.science/api/pith-number/PCBUXUOUOK4XBGY7BOBTVKL5IO/graph.json","events_json":"https://pith.science/api/pith-number/PCBUXUOUOK4XBGY7BOBTVKL5IO/events.json","paper":"https://pith.science/paper/PCBUXUOU"},"agent_actions":{"view_html":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO","download_json":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO.json","view_paper":"https://pith.science/paper/PCBUXUOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12688&json=true","fetch_graph":"https://pith.science/api/pith-number/PCBUXUOUOK4XBGY7BOBTVKL5IO/graph.json","fetch_events":"https://pith.science/api/pith-number/PCBUXUOUOK4XBGY7BOBTVKL5IO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO/action/storage_attestation","attest_author":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO/action/author_attestation","sign_citation":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO/action/citation_signature","submit_replication":"https://pith.science/pith/PCBUXUOUOK4XBGY7BOBTVKL5IO/action/replication_record"}},"created_at":"2026-07-05T06:04:19.815244+00:00","updated_at":"2026-07-05T06:04:19.815244+00:00"}