{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UIY7GH66VCRLT4UZ2X4CLYG6WS","short_pith_number":"pith:UIY7GH66","schema_version":"1.0","canonical_sha256":"a231f31fdea8a2b9f299d5f825e0deb4aee4fe8851b5046d94adcbd48adabe17","source":{"kind":"arxiv","id":"2109.11165","version":4},"attestation_state":"computed","paper":{"title":"A Lightweight dynamic filter for keyword spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"David K. Han, Donghyeon Kim, Hanseok Ko, Jeonggi Kwak, Kyungdeuk Ko","submitted_at":"2021-09-23T06:47:09Z","abstract_excerpt":"Keyword Spotting (KWS) from speech signals is widely applied to perform fully hands-free speech recognition. The KWS network is designed as a small-footprint model so it can continuously be active. Recent efforts have explored dynamic filter-based models in deep learning frameworks to enhance the system's robustness or accuracy. However, as a dynamic filter framework requires high computational costs, the implementation is limited to the computational condition of the device. In this paper, we propose a lightweight dynamic filter to improve the performance of KWS. Our proposed model divides th"},"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":"2109.11165","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-09-23T06:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"ec95d3c901238774a2eda4b4c8b928afe41ce6d80d18420f9780dcaa4ca192ac","abstract_canon_sha256":"4803f96c8a0425a8f06d984202d635d555b5bfb1457378c6280a77bfb67de370"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:01.561786Z","signature_b64":"P3JReuzaAt8554WMzvpamm57BGDVlk5l8AZB8zn1Arem6E+g9B9isdbavDKv74acmHkrkZaQLnYM2L+CL9ZbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a231f31fdea8a2b9f299d5f825e0deb4aee4fe8851b5046d94adcbd48adabe17","last_reissued_at":"2026-07-05T07:27:01.561303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:01.561303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Lightweight dynamic filter for keyword spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"David K. Han, Donghyeon Kim, Hanseok Ko, Jeonggi Kwak, Kyungdeuk Ko","submitted_at":"2021-09-23T06:47:09Z","abstract_excerpt":"Keyword Spotting (KWS) from speech signals is widely applied to perform fully hands-free speech recognition. The KWS network is designed as a small-footprint model so it can continuously be active. Recent efforts have explored dynamic filter-based models in deep learning frameworks to enhance the system's robustness or accuracy. However, as a dynamic filter framework requires high computational costs, the implementation is limited to the computational condition of the device. In this paper, we propose a lightweight dynamic filter to improve the performance of KWS. Our proposed model divides th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11165","kind":"arxiv","version":4},"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/2109.11165/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":"2109.11165","created_at":"2026-07-05T07:27:01.561380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.11165v4","created_at":"2026-07-05T07:27:01.561380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11165","created_at":"2026-07-05T07:27:01.561380+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIY7GH66VCRL","created_at":"2026-07-05T07:27:01.561380+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIY7GH66VCRLT4UZ","created_at":"2026-07-05T07:27:01.561380+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIY7GH66","created_at":"2026-07-05T07:27:01.561380+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/UIY7GH66VCRLT4UZ2X4CLYG6WS","json":"https://pith.science/pith/UIY7GH66VCRLT4UZ2X4CLYG6WS.json","graph_json":"https://pith.science/api/pith-number/UIY7GH66VCRLT4UZ2X4CLYG6WS/graph.json","events_json":"https://pith.science/api/pith-number/UIY7GH66VCRLT4UZ2X4CLYG6WS/events.json","paper":"https://pith.science/paper/UIY7GH66"},"agent_actions":{"view_html":"https://pith.science/pith/UIY7GH66VCRLT4UZ2X4CLYG6WS","download_json":"https://pith.science/pith/UIY7GH66VCRLT4UZ2X4CLYG6WS.json","view_paper":"https://pith.science/paper/UIY7GH66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.11165&json=true","fetch_graph":"https://pith.science/api/pith-number/UIY7GH66VCRLT4UZ2X4CLYG6WS/graph.json","fetch_events":"https://pith.science/api/pith-number/UIY7GH66VCRLT4UZ2X4CLYG6WS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIY7GH66VCRLT4UZ2X4CLYG6WS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIY7GH66VCRLT4UZ2X4CLYG6WS/action/storage_attestation","attest_author":"https://pith.science/pith/UIY7GH66VCRLT4UZ2X4CLYG6WS/action/author_attestation","sign_citation":"https://pith.science/pith/UIY7GH66VCRLT4UZ2X4CLYG6WS/action/citation_signature","submit_replication":"https://pith.science/pith/UIY7GH66VCRLT4UZ2X4CLYG6WS/action/replication_record"}},"created_at":"2026-07-05T07:27:01.561380+00:00","updated_at":"2026-07-05T07:27:01.561380+00:00"}