{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GQBNEOSDJNSY57CF7UQO4IORVK","short_pith_number":"pith:GQBNEOSD","schema_version":"1.0","canonical_sha256":"3402d23a434b658efc45fd20ee21d1aa914c6e0b13a5e77716c5e8868c15626f","source":{"kind":"arxiv","id":"2209.11377","version":1},"attestation_state":"computed","paper":{"title":"UniKW-AT: Unified Keyword Spotting and Audio Tagging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2022-09-23T02:39:59Z","abstract_excerpt":"Within the audio research community and the industry, keyword spotting (KWS) and audio tagging (AT) are seen as two distinct tasks and research fields. However, from a technical point of view, both of these tasks are identical: they predict a label (keyword in KWS, sound event in AT) for some fixed-sized input audio segment. This work proposes UniKW-AT: An initial approach for jointly training both KWS and AT. UniKW-AT enhances the noise-robustness for KWS, while also being able to predict specific sound events and enabling conditional wake-ups on sound events. Our approach extends the AT pipe"},"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":"2209.11377","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-09-23T02:39:59Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6750bd8fee46bdeda51e548098ef2352d7a04b3fe5a08eb251196d464800bf8c","abstract_canon_sha256":"bce30fa1febb7e1f9da398f22abc21ffdb6108a5caca7068ae257f37a3dc4767"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:19.858502Z","signature_b64":"Ot0jxc0JbVElA0qDdcc18Cdgw7F6HW1iw0nkYYwG4CMnkqNh28hhKEfFQBkfaH2PUQI2biUHWRp5fsm7MIPSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3402d23a434b658efc45fd20ee21d1aa914c6e0b13a5e77716c5e8868c15626f","last_reissued_at":"2026-07-05T05:00:19.858118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:19.858118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniKW-AT: Unified Keyword Spotting and Audio Tagging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2022-09-23T02:39:59Z","abstract_excerpt":"Within the audio research community and the industry, keyword spotting (KWS) and audio tagging (AT) are seen as two distinct tasks and research fields. However, from a technical point of view, both of these tasks are identical: they predict a label (keyword in KWS, sound event in AT) for some fixed-sized input audio segment. This work proposes UniKW-AT: An initial approach for jointly training both KWS and AT. UniKW-AT enhances the noise-robustness for KWS, while also being able to predict specific sound events and enabling conditional wake-ups on sound events. Our approach extends the AT pipe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11377","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/2209.11377/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":"2209.11377","created_at":"2026-07-05T05:00:19.858173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11377v1","created_at":"2026-07-05T05:00:19.858173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11377","created_at":"2026-07-05T05:00:19.858173+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQBNEOSDJNSY","created_at":"2026-07-05T05:00:19.858173+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQBNEOSDJNSY57CF","created_at":"2026-07-05T05:00:19.858173+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQBNEOSD","created_at":"2026-07-05T05:00:19.858173+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/GQBNEOSDJNSY57CF7UQO4IORVK","json":"https://pith.science/pith/GQBNEOSDJNSY57CF7UQO4IORVK.json","graph_json":"https://pith.science/api/pith-number/GQBNEOSDJNSY57CF7UQO4IORVK/graph.json","events_json":"https://pith.science/api/pith-number/GQBNEOSDJNSY57CF7UQO4IORVK/events.json","paper":"https://pith.science/paper/GQBNEOSD"},"agent_actions":{"view_html":"https://pith.science/pith/GQBNEOSDJNSY57CF7UQO4IORVK","download_json":"https://pith.science/pith/GQBNEOSDJNSY57CF7UQO4IORVK.json","view_paper":"https://pith.science/paper/GQBNEOSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11377&json=true","fetch_graph":"https://pith.science/api/pith-number/GQBNEOSDJNSY57CF7UQO4IORVK/graph.json","fetch_events":"https://pith.science/api/pith-number/GQBNEOSDJNSY57CF7UQO4IORVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQBNEOSDJNSY57CF7UQO4IORVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQBNEOSDJNSY57CF7UQO4IORVK/action/storage_attestation","attest_author":"https://pith.science/pith/GQBNEOSDJNSY57CF7UQO4IORVK/action/author_attestation","sign_citation":"https://pith.science/pith/GQBNEOSDJNSY57CF7UQO4IORVK/action/citation_signature","submit_replication":"https://pith.science/pith/GQBNEOSDJNSY57CF7UQO4IORVK/action/replication_record"}},"created_at":"2026-07-05T05:00:19.858173+00:00","updated_at":"2026-07-05T05:00:19.858173+00:00"}