{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FDYW63LKEFRKACQBZHAEJQRVC4","short_pith_number":"pith:FDYW63LK","schema_version":"1.0","canonical_sha256":"28f16f6d6a2162a00a01c9c044c23517159b967c835e2f83a585db76b2db7d69","source":{"kind":"arxiv","id":"2408.13355","version":1},"attestation_state":"computed","paper":{"title":"Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Biqiao Zhang, Li Wan, Ming Sun, Shang-Wen Li, Xin Lei, Yiteng Huang, Zhaojun Yang, Zhenyu Wang","submitted_at":"2024-08-23T20:03:51Z","abstract_excerpt":"A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a small-footprint and high-performing KWS model with robustness under different acoustic environments. In this paper, we explore how to effectively apply adversarial examples to improve KWS robustness. We propose datasource-aware disentangled learning with adversarial examples to reduce the mismatch between the original and adversarial data as well as the mismatch across original training datasources. The KWS model arch"},"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":"2408.13355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-23T20:03:51Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"88a5bde9901698338a717366cb19e28d331be29026d276e81d331f36b0ac9c13","abstract_canon_sha256":"e6475ed7a1314f9b3bb07256ea16a938c09594cdbd531e226261ba0a6c2f666a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:49.270243Z","signature_b64":"6KfjOzIGs3D8U3L38IAcYLs+AiEWm3gR2D8fy+akwDZelq5lAVNKkiIjW5x9yf2lzFyhNA37+AfYZ2cUTQN5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28f16f6d6a2162a00a01c9c044c23517159b967c835e2f83a585db76b2db7d69","last_reissued_at":"2026-07-05T08:58:49.269641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:49.269641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Biqiao Zhang, Li Wan, Ming Sun, Shang-Wen Li, Xin Lei, Yiteng Huang, Zhaojun Yang, Zhenyu Wang","submitted_at":"2024-08-23T20:03:51Z","abstract_excerpt":"A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a small-footprint and high-performing KWS model with robustness under different acoustic environments. In this paper, we explore how to effectively apply adversarial examples to improve KWS robustness. We propose datasource-aware disentangled learning with adversarial examples to reduce the mismatch between the original and adversarial data as well as the mismatch across original training datasources. The KWS model arch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13355","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/2408.13355/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":"2408.13355","created_at":"2026-07-05T08:58:49.269700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13355v1","created_at":"2026-07-05T08:58:49.269700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13355","created_at":"2026-07-05T08:58:49.269700+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDYW63LKEFRK","created_at":"2026-07-05T08:58:49.269700+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDYW63LKEFRKACQB","created_at":"2026-07-05T08:58:49.269700+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDYW63LK","created_at":"2026-07-05T08:58:49.269700+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/FDYW63LKEFRKACQBZHAEJQRVC4","json":"https://pith.science/pith/FDYW63LKEFRKACQBZHAEJQRVC4.json","graph_json":"https://pith.science/api/pith-number/FDYW63LKEFRKACQBZHAEJQRVC4/graph.json","events_json":"https://pith.science/api/pith-number/FDYW63LKEFRKACQBZHAEJQRVC4/events.json","paper":"https://pith.science/paper/FDYW63LK"},"agent_actions":{"view_html":"https://pith.science/pith/FDYW63LKEFRKACQBZHAEJQRVC4","download_json":"https://pith.science/pith/FDYW63LKEFRKACQBZHAEJQRVC4.json","view_paper":"https://pith.science/paper/FDYW63LK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13355&json=true","fetch_graph":"https://pith.science/api/pith-number/FDYW63LKEFRKACQBZHAEJQRVC4/graph.json","fetch_events":"https://pith.science/api/pith-number/FDYW63LKEFRKACQBZHAEJQRVC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDYW63LKEFRKACQBZHAEJQRVC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDYW63LKEFRKACQBZHAEJQRVC4/action/storage_attestation","attest_author":"https://pith.science/pith/FDYW63LKEFRKACQBZHAEJQRVC4/action/author_attestation","sign_citation":"https://pith.science/pith/FDYW63LKEFRKACQBZHAEJQRVC4/action/citation_signature","submit_replication":"https://pith.science/pith/FDYW63LKEFRKACQBZHAEJQRVC4/action/replication_record"}},"created_at":"2026-07-05T08:58:49.269700+00:00","updated_at":"2026-07-05T08:58:49.269700+00:00"}