{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DZ3YIPSL7MV6SMAAZSKF34A4OK","short_pith_number":"pith:DZ3YIPSL","schema_version":"1.0","canonical_sha256":"1e77843e4bfb2be93000cc945df01c728a5db939ae39b543c8880686b5a891b7","source":{"kind":"arxiv","id":"2206.13708","version":1},"attestation_state":"computed","paper":{"title":"Personalized Keyword Spotting through Multi-task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Byeonggeun Kim, Inseop Chung, Seunghan Yang, Simyung Chang","submitted_at":"2022-06-28T02:48:34Z","abstract_excerpt":"Keyword spotting (KWS) plays an essential role in enabling speech-based user interaction on smart devices, and conventional KWS (C-KWS) approaches have concentrated on detecting user-agnostic pre-defined keywords. However, in practice, most user interactions come from target users enrolled in the device which motivates to construct personalized keyword spotting. We design two personalized KWS tasks; (1) Target user Biased KWS (TB-KWS) and (2) Target user Only KWS (TO-KWS). To solve the tasks, we propose personalized keyword spotting through multi-task learning (PK-MTL) that consists of multi-t"},"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":"2206.13708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-06-28T02:48:34Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"7d0406e96ca41ef633bd1194a4690e9412afe149c862b59fc36b8f78fa871c58","abstract_canon_sha256":"742bbd8435711c3c513adeaf17dd373b6d021546d99e7788ae51c0103a2a8b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:24.086014Z","signature_b64":"jsF+1cLpg6KpHyx7DMZHRg70Qn1GvEXCCRc/k/hcwyH5aOFCVhPLn5avxPPadMl0NrxGJF3oa81mSfu9wSEBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e77843e4bfb2be93000cc945df01c728a5db939ae39b543c8880686b5a891b7","last_reissued_at":"2026-07-05T04:35:24.085498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:24.085498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Keyword Spotting through Multi-task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Byeonggeun Kim, Inseop Chung, Seunghan Yang, Simyung Chang","submitted_at":"2022-06-28T02:48:34Z","abstract_excerpt":"Keyword spotting (KWS) plays an essential role in enabling speech-based user interaction on smart devices, and conventional KWS (C-KWS) approaches have concentrated on detecting user-agnostic pre-defined keywords. However, in practice, most user interactions come from target users enrolled in the device which motivates to construct personalized keyword spotting. We design two personalized KWS tasks; (1) Target user Biased KWS (TB-KWS) and (2) Target user Only KWS (TO-KWS). To solve the tasks, we propose personalized keyword spotting through multi-task learning (PK-MTL) that consists of multi-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13708","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/2206.13708/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":"2206.13708","created_at":"2026-07-05T04:35:24.085564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.13708v1","created_at":"2026-07-05T04:35:24.085564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13708","created_at":"2026-07-05T04:35:24.085564+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZ3YIPSL7MV6","created_at":"2026-07-05T04:35:24.085564+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZ3YIPSL7MV6SMAA","created_at":"2026-07-05T04:35:24.085564+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZ3YIPSL","created_at":"2026-07-05T04:35:24.085564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11817","citing_title":"AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK","json":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK.json","graph_json":"https://pith.science/api/pith-number/DZ3YIPSL7MV6SMAAZSKF34A4OK/graph.json","events_json":"https://pith.science/api/pith-number/DZ3YIPSL7MV6SMAAZSKF34A4OK/events.json","paper":"https://pith.science/paper/DZ3YIPSL"},"agent_actions":{"view_html":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK","download_json":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK.json","view_paper":"https://pith.science/paper/DZ3YIPSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.13708&json=true","fetch_graph":"https://pith.science/api/pith-number/DZ3YIPSL7MV6SMAAZSKF34A4OK/graph.json","fetch_events":"https://pith.science/api/pith-number/DZ3YIPSL7MV6SMAAZSKF34A4OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK/action/storage_attestation","attest_author":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK/action/author_attestation","sign_citation":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK/action/citation_signature","submit_replication":"https://pith.science/pith/DZ3YIPSL7MV6SMAAZSKF34A4OK/action/replication_record"}},"created_at":"2026-07-05T04:35:24.085564+00:00","updated_at":"2026-07-05T04:35:24.085564+00:00"}