{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EKE52JRS5BUJPSDXMXDSUK754G","short_pith_number":"pith:EKE52JRS","schema_version":"1.0","canonical_sha256":"2289dd2632e86897c87765c72a2bfde186c92d99b97a7f3f8b8b72d1f5efd537","source":{"kind":"arxiv","id":"2312.09760","version":1},"attestation_state":"computed","paper":{"title":"U2-KWS: Unified Two-pass Open-vocabulary Keyword Spotting with Keyword Bias","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ao Zhang, Kaixun Huang, Lei Xie, Ming Liu, Pan Zhou, Yong Zou","submitted_at":"2023-12-15T13:00:42Z","abstract_excerpt":"Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest. However, existing methods based on acoustic models and post-processing train the acoustic model with ASR training criteria to model all phonemes, making the acoustic model under-optimized for the KWS task. To solve this problem, we propose a novel unified two-pass open-vocabulary KWS (U2-KWS) framework inspired by the two-pass ASR model U2. Specifically, we employ the CTC branch as the first stage model to detect potential keyword candidates and the decoder branch as the "},"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":"2312.09760","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-12-15T13:00:42Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"de30bd07e84a19d5e18ae8fbc5c708b4e20d34ebff59b0474b906bf53d649fc3","abstract_canon_sha256":"ad8fea9557aca8c0b91c3b24bc4943bb06a7bb29c2dc38624e9b3759c92da8d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:40.302927Z","signature_b64":"0rgNztB+mjk9iDTGVvarbTJiHZxbWTfyDfAaZqUNLbRH43/jFksPCkDulC4nZEYC1zQRa9EGRT2kfpRONqI9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2289dd2632e86897c87765c72a2bfde186c92d99b97a7f3f8b8b72d1f5efd537","last_reissued_at":"2026-07-05T07:24:40.302514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:40.302514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"U2-KWS: Unified Two-pass Open-vocabulary Keyword Spotting with Keyword Bias","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ao Zhang, Kaixun Huang, Lei Xie, Ming Liu, Pan Zhou, Yong Zou","submitted_at":"2023-12-15T13:00:42Z","abstract_excerpt":"Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest. However, existing methods based on acoustic models and post-processing train the acoustic model with ASR training criteria to model all phonemes, making the acoustic model under-optimized for the KWS task. To solve this problem, we propose a novel unified two-pass open-vocabulary KWS (U2-KWS) framework inspired by the two-pass ASR model U2. Specifically, we employ the CTC branch as the first stage model to detect potential keyword candidates and the decoder branch as the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09760","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/2312.09760/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":"2312.09760","created_at":"2026-07-05T07:24:40.302574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09760v1","created_at":"2026-07-05T07:24:40.302574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09760","created_at":"2026-07-05T07:24:40.302574+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKE52JRS5BUJ","created_at":"2026-07-05T07:24:40.302574+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKE52JRS5BUJPSDX","created_at":"2026-07-05T07:24:40.302574+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKE52JRS","created_at":"2026-07-05T07:24:40.302574+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/EKE52JRS5BUJPSDXMXDSUK754G","json":"https://pith.science/pith/EKE52JRS5BUJPSDXMXDSUK754G.json","graph_json":"https://pith.science/api/pith-number/EKE52JRS5BUJPSDXMXDSUK754G/graph.json","events_json":"https://pith.science/api/pith-number/EKE52JRS5BUJPSDXMXDSUK754G/events.json","paper":"https://pith.science/paper/EKE52JRS"},"agent_actions":{"view_html":"https://pith.science/pith/EKE52JRS5BUJPSDXMXDSUK754G","download_json":"https://pith.science/pith/EKE52JRS5BUJPSDXMXDSUK754G.json","view_paper":"https://pith.science/paper/EKE52JRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09760&json=true","fetch_graph":"https://pith.science/api/pith-number/EKE52JRS5BUJPSDXMXDSUK754G/graph.json","fetch_events":"https://pith.science/api/pith-number/EKE52JRS5BUJPSDXMXDSUK754G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKE52JRS5BUJPSDXMXDSUK754G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKE52JRS5BUJPSDXMXDSUK754G/action/storage_attestation","attest_author":"https://pith.science/pith/EKE52JRS5BUJPSDXMXDSUK754G/action/author_attestation","sign_citation":"https://pith.science/pith/EKE52JRS5BUJPSDXMXDSUK754G/action/citation_signature","submit_replication":"https://pith.science/pith/EKE52JRS5BUJPSDXMXDSUK754G/action/replication_record"}},"created_at":"2026-07-05T07:24:40.302574+00:00","updated_at":"2026-07-05T07:24:40.302574+00:00"}