{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UTLH646DJDYHHY6HMTLLGGL2JV","short_pith_number":"pith:UTLH646D","schema_version":"1.0","canonical_sha256":"a4d67f73c348f073e3c764d6b3197a4d4149007e34d7c75c9a8e2b5c5e65e99a","source":{"kind":"arxiv","id":"2605.22120","version":1},"attestation_state":"computed","paper":{"title":"Effective User-defined Keyword Spotting with Dual-stage Matching, Multi-modal Enrollment, and Continual Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Han Cheng, Shiyi Mu, Shugong Xu, Xinnuo Li, Yongjin Zhou, Zhiqi Ai","submitted_at":"2026-05-21T07:52:21Z","abstract_excerpt":"User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable words, (2) performance inconsistency across speakers with varying pronunciations, and (3) high data cost to ensure reliable wake-word performance. In this paper, we introduce DMA-KWS, an efficient and robust framework for user-defined keyword spotting. First, it adopts a dual-stage matching pipeline: CTC decoding with streaming phoneme search to locate candidate segments, followed by QbyT with a phoneme matcher for f"},"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":"2605.22120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-21T07:52:21Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"237a72ca1c1e96b26283629b84189073d25ab556a2a8df6960444d13090c4d3c","abstract_canon_sha256":"86852f4ec055343fdbca0f3085c1329a99ebfe58b8d7bd8a4edbbc877fa3e63c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:26.866618Z","signature_b64":"VK9fxJWBgWUJBtRsZD23Q7P8i/xfU3DOFjIZckWUnubrjT5YJqJh+ky4YPkB95wcqRz/MCPjiv2iUl/UfGSmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4d67f73c348f073e3c764d6b3197a4d4149007e34d7c75c9a8e2b5c5e65e99a","last_reissued_at":"2026-05-22T01:04:26.865738Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:26.865738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective User-defined Keyword Spotting with Dual-stage Matching, Multi-modal Enrollment, and Continual Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Han Cheng, Shiyi Mu, Shugong Xu, Xinnuo Li, Yongjin Zhou, Zhiqi Ai","submitted_at":"2026-05-21T07:52:21Z","abstract_excerpt":"User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable words, (2) performance inconsistency across speakers with varying pronunciations, and (3) high data cost to ensure reliable wake-word performance. In this paper, we introduce DMA-KWS, an efficient and robust framework for user-defined keyword spotting. First, it adopts a dual-stage matching pipeline: CTC decoding with streaming phoneme search to locate candidate segments, followed by QbyT with a phoneme matcher for f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22120","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/2605.22120/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":"2605.22120","created_at":"2026-05-22T01:04:26.865896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22120v1","created_at":"2026-05-22T01:04:26.865896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22120","created_at":"2026-05-22T01:04:26.865896+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTLH646DJDYH","created_at":"2026-05-22T01:04:26.865896+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTLH646DJDYHHY6H","created_at":"2026-05-22T01:04:26.865896+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTLH646D","created_at":"2026-05-22T01:04:26.865896+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/UTLH646DJDYHHY6HMTLLGGL2JV","json":"https://pith.science/pith/UTLH646DJDYHHY6HMTLLGGL2JV.json","graph_json":"https://pith.science/api/pith-number/UTLH646DJDYHHY6HMTLLGGL2JV/graph.json","events_json":"https://pith.science/api/pith-number/UTLH646DJDYHHY6HMTLLGGL2JV/events.json","paper":"https://pith.science/paper/UTLH646D"},"agent_actions":{"view_html":"https://pith.science/pith/UTLH646DJDYHHY6HMTLLGGL2JV","download_json":"https://pith.science/pith/UTLH646DJDYHHY6HMTLLGGL2JV.json","view_paper":"https://pith.science/paper/UTLH646D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22120&json=true","fetch_graph":"https://pith.science/api/pith-number/UTLH646DJDYHHY6HMTLLGGL2JV/graph.json","fetch_events":"https://pith.science/api/pith-number/UTLH646DJDYHHY6HMTLLGGL2JV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTLH646DJDYHHY6HMTLLGGL2JV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTLH646DJDYHHY6HMTLLGGL2JV/action/storage_attestation","attest_author":"https://pith.science/pith/UTLH646DJDYHHY6HMTLLGGL2JV/action/author_attestation","sign_citation":"https://pith.science/pith/UTLH646DJDYHHY6HMTLLGGL2JV/action/citation_signature","submit_replication":"https://pith.science/pith/UTLH646DJDYHHY6HMTLLGGL2JV/action/replication_record"}},"created_at":"2026-05-22T01:04:26.865896+00:00","updated_at":"2026-05-22T01:04:26.865896+00:00"}