{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:62OFU3S3IHB7ACINW7M6O7XQ4K","short_pith_number":"pith:62OFU3S3","schema_version":"1.0","canonical_sha256":"f69c5a6e5b41c3f0090db7d9e77ef0e28b684ef705fe7a4a6636a52fc63645d0","source":{"kind":"arxiv","id":"2606.20106","version":1},"attestation_state":"computed","paper":{"title":"Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Berlin Chen, Chien-Chun Wang, Hung-Shin Lee, Kuan-Tang Huang, Ming-Hsiang Hu","submitted_at":"2026-06-18T11:29:49Z","abstract_excerpt":"User-defined keyword spotting (UD-KWS) enables zero-shot wake-word detection from text, but existing systems learn speaker-invariant representations that cannot reject impostors uttering the correct keyword. We address this dual zero-shot setting -- unseen keywords and unseen speakers -- with ZP-KWS, a lightweight framework combining a phoneme-supervised audio encoder with a GE2E-pretrained compact speaker encoder (about 0.9M parameters). Multiplicative late fusion at inference grants each branch independent veto power, supporting modes from conventional detection to strict speaker-gated activ"},"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":"2606.20106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T11:29:49Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"65fc0f877aac6e4b4da404cf31cfcca3258d79578343e2a2ff40279354b892e4","abstract_canon_sha256":"1ffe1f8f833c05b23671512a3f9f8d9a5b0b97945292ce47361091d4a5f571fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:03.014132Z","signature_b64":"8xFD71JlP8d9Y74mD3PKOhcL/bLD20Ai+Hwe0wbHH4A3RPjPWyHMVVguG8BP4P0xMKrcU5xrzb4xvH1CEsy0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f69c5a6e5b41c3f0090db7d9e77ef0e28b684ef705fe7a4a6636a52fc63645d0","last_reissued_at":"2026-06-19T16:13:03.013717Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:03.013717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Berlin Chen, Chien-Chun Wang, Hung-Shin Lee, Kuan-Tang Huang, Ming-Hsiang Hu","submitted_at":"2026-06-18T11:29:49Z","abstract_excerpt":"User-defined keyword spotting (UD-KWS) enables zero-shot wake-word detection from text, but existing systems learn speaker-invariant representations that cannot reject impostors uttering the correct keyword. We address this dual zero-shot setting -- unseen keywords and unseen speakers -- with ZP-KWS, a lightweight framework combining a phoneme-supervised audio encoder with a GE2E-pretrained compact speaker encoder (about 0.9M parameters). Multiplicative late fusion at inference grants each branch independent veto power, supporting modes from conventional detection to strict speaker-gated activ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20106","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/2606.20106/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":"2606.20106","created_at":"2026-06-19T16:13:03.013783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20106v1","created_at":"2026-06-19T16:13:03.013783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20106","created_at":"2026-06-19T16:13:03.013783+00:00"},{"alias_kind":"pith_short_12","alias_value":"62OFU3S3IHB7","created_at":"2026-06-19T16:13:03.013783+00:00"},{"alias_kind":"pith_short_16","alias_value":"62OFU3S3IHB7ACIN","created_at":"2026-06-19T16:13:03.013783+00:00"},{"alias_kind":"pith_short_8","alias_value":"62OFU3S3","created_at":"2026-06-19T16:13:03.013783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.20106","citing_title":"Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K","json":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K.json","graph_json":"https://pith.science/api/pith-number/62OFU3S3IHB7ACINW7M6O7XQ4K/graph.json","events_json":"https://pith.science/api/pith-number/62OFU3S3IHB7ACINW7M6O7XQ4K/events.json","paper":"https://pith.science/paper/62OFU3S3"},"agent_actions":{"view_html":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K","download_json":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K.json","view_paper":"https://pith.science/paper/62OFU3S3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20106&json=true","fetch_graph":"https://pith.science/api/pith-number/62OFU3S3IHB7ACINW7M6O7XQ4K/graph.json","fetch_events":"https://pith.science/api/pith-number/62OFU3S3IHB7ACINW7M6O7XQ4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K/action/storage_attestation","attest_author":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K/action/author_attestation","sign_citation":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K/action/citation_signature","submit_replication":"https://pith.science/pith/62OFU3S3IHB7ACINW7M6O7XQ4K/action/replication_record"}},"created_at":"2026-06-19T16:13:03.013783+00:00","updated_at":"2026-06-19T16:13:03.013783+00:00"}