{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JLMM4XW7ISCCEOPXZEE27RLEEI","short_pith_number":"pith:JLMM4XW7","schema_version":"1.0","canonical_sha256":"4ad8ce5edf44842239f7c909afc5642204ce34f50b28081bc60ffccd60d9d881","source":{"kind":"arxiv","id":"2409.00099","version":2},"attestation_state":"computed","paper":{"title":"Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Biqiao Zhang, Li Wan, Ming Sun, Mumin Jin, Shuyu Kong, Xin Lei, Yiteng Huang, Zhaojun Yang, Zhenyu Wang","submitted_at":"2024-08-27T03:44:57Z","abstract_excerpt":"Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is crucial for tailoring interactions with intelligent devices. In this paper, we present a novel Query-by-Example (QbyE) KWS system that employs spectral-temporal graph attentive pooling and multi-task learning. This framework aims to effectively learn speaker-invariant and linguistic-informative embeddings for QbyE KWS tasks. Within this framework, we investigate three distinct network architectures for encoder modeling: LiCoNet, Conformer and ECAPA_TDNN"},"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":"2409.00099","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T03:44:57Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"97eaf24887f6eba94e3687c9a12ce4a5c269e59167ff403a07cea8e2f3ac95e0","abstract_canon_sha256":"a180176ff3d7865c3a2adb39ecfabca1b5dff9b881f028e4731ac2f7943f7499"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:26.423002Z","signature_b64":"A9xyp8X+izpDqhH4AIyoNr+m4fklrVrUGa4uxWSGUlIIOxp7tO7nyqOM/YHZrHCa28R4I/iHFxE24zbYxvkSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ad8ce5edf44842239f7c909afc5642204ce34f50b28081bc60ffccd60d9d881","last_reissued_at":"2026-07-05T09:39:26.422496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:26.422496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Biqiao Zhang, Li Wan, Ming Sun, Mumin Jin, Shuyu Kong, Xin Lei, Yiteng Huang, Zhaojun Yang, Zhenyu Wang","submitted_at":"2024-08-27T03:44:57Z","abstract_excerpt":"Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is crucial for tailoring interactions with intelligent devices. In this paper, we present a novel Query-by-Example (QbyE) KWS system that employs spectral-temporal graph attentive pooling and multi-task learning. This framework aims to effectively learn speaker-invariant and linguistic-informative embeddings for QbyE KWS tasks. Within this framework, we investigate three distinct network architectures for encoder modeling: LiCoNet, Conformer and ECAPA_TDNN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00099","kind":"arxiv","version":2},"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/2409.00099/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":"2409.00099","created_at":"2026-07-05T09:39:26.422557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00099v2","created_at":"2026-07-05T09:39:26.422557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00099","created_at":"2026-07-05T09:39:26.422557+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLMM4XW7ISCC","created_at":"2026-07-05T09:39:26.422557+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLMM4XW7ISCCEOPX","created_at":"2026-07-05T09:39:26.422557+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLMM4XW7","created_at":"2026-07-05T09:39:26.422557+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/JLMM4XW7ISCCEOPXZEE27RLEEI","json":"https://pith.science/pith/JLMM4XW7ISCCEOPXZEE27RLEEI.json","graph_json":"https://pith.science/api/pith-number/JLMM4XW7ISCCEOPXZEE27RLEEI/graph.json","events_json":"https://pith.science/api/pith-number/JLMM4XW7ISCCEOPXZEE27RLEEI/events.json","paper":"https://pith.science/paper/JLMM4XW7"},"agent_actions":{"view_html":"https://pith.science/pith/JLMM4XW7ISCCEOPXZEE27RLEEI","download_json":"https://pith.science/pith/JLMM4XW7ISCCEOPXZEE27RLEEI.json","view_paper":"https://pith.science/paper/JLMM4XW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00099&json=true","fetch_graph":"https://pith.science/api/pith-number/JLMM4XW7ISCCEOPXZEE27RLEEI/graph.json","fetch_events":"https://pith.science/api/pith-number/JLMM4XW7ISCCEOPXZEE27RLEEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLMM4XW7ISCCEOPXZEE27RLEEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLMM4XW7ISCCEOPXZEE27RLEEI/action/storage_attestation","attest_author":"https://pith.science/pith/JLMM4XW7ISCCEOPXZEE27RLEEI/action/author_attestation","sign_citation":"https://pith.science/pith/JLMM4XW7ISCCEOPXZEE27RLEEI/action/citation_signature","submit_replication":"https://pith.science/pith/JLMM4XW7ISCCEOPXZEE27RLEEI/action/replication_record"}},"created_at":"2026-07-05T09:39:26.422557+00:00","updated_at":"2026-07-05T09:39:26.422557+00:00"}