{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VFIS3C2AH5NBEQAKXEEYTXDCXB","short_pith_number":"pith:VFIS3C2A","schema_version":"1.0","canonical_sha256":"a9512d8b403f5a12400ab90989dc62b848098228643b1e468734e5dceb5f1a7a","source":{"kind":"arxiv","id":"2406.12447","version":1},"attestation_state":"computed","paper":{"title":"Text-aware Speech Separation for Multi-talker Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Baochen Yang, Hao Li, Haoyu Li, Kai Yu, Linfeng Yu, Tian Tan, Yu Xi","submitted_at":"2024-06-18T09:48:59Z","abstract_excerpt":"For noisy environments, ensuring the robustness of keyword spotting (KWS) systems is essential. While much research has focused on noisy KWS, less attention has been paid to multi-talker mixed speech scenarios. Unlike the usual cocktail party problem where multi-talker speech is separated using speaker clues, the key challenge here is to extract the target speech for KWS based on text clues. To address it, this paper proposes a novel Text-aware Permutation Determinization Training method for multi-talker KWS with a clue-based Speech Separation front-end (TPDT-SS). Our research highlights the c"},"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":"2406.12447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T09:48:59Z","cross_cats_sorted":[],"title_canon_sha256":"aab2f2cd07a3c09745053e6c426ac4b3a496b82a7ff8decce14720a0605f0503","abstract_canon_sha256":"f7b7ed7b225b87dcf92e8fb3752c36a8e8961a14407c9c489eaca107de06a551"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:46.442696Z","signature_b64":"qlwdF5bHvuOeMg+AsUvMMJ7+Ybj/+GppEstfJLqgcAxBnhm+Z5PDaSKtLi3nlj5o6u15wk1G3WyK/aimOO7vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9512d8b403f5a12400ab90989dc62b848098228643b1e468734e5dceb5f1a7a","last_reissued_at":"2026-07-05T08:33:46.442275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:46.442275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-aware Speech Separation for Multi-talker Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Baochen Yang, Hao Li, Haoyu Li, Kai Yu, Linfeng Yu, Tian Tan, Yu Xi","submitted_at":"2024-06-18T09:48:59Z","abstract_excerpt":"For noisy environments, ensuring the robustness of keyword spotting (KWS) systems is essential. While much research has focused on noisy KWS, less attention has been paid to multi-talker mixed speech scenarios. Unlike the usual cocktail party problem where multi-talker speech is separated using speaker clues, the key challenge here is to extract the target speech for KWS based on text clues. To address it, this paper proposes a novel Text-aware Permutation Determinization Training method for multi-talker KWS with a clue-based Speech Separation front-end (TPDT-SS). Our research highlights the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12447","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/2406.12447/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":"2406.12447","created_at":"2026-07-05T08:33:46.442340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12447v1","created_at":"2026-07-05T08:33:46.442340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12447","created_at":"2026-07-05T08:33:46.442340+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFIS3C2AH5NB","created_at":"2026-07-05T08:33:46.442340+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFIS3C2AH5NBEQAK","created_at":"2026-07-05T08:33:46.442340+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFIS3C2A","created_at":"2026-07-05T08:33:46.442340+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/VFIS3C2AH5NBEQAKXEEYTXDCXB","json":"https://pith.science/pith/VFIS3C2AH5NBEQAKXEEYTXDCXB.json","graph_json":"https://pith.science/api/pith-number/VFIS3C2AH5NBEQAKXEEYTXDCXB/graph.json","events_json":"https://pith.science/api/pith-number/VFIS3C2AH5NBEQAKXEEYTXDCXB/events.json","paper":"https://pith.science/paper/VFIS3C2A"},"agent_actions":{"view_html":"https://pith.science/pith/VFIS3C2AH5NBEQAKXEEYTXDCXB","download_json":"https://pith.science/pith/VFIS3C2AH5NBEQAKXEEYTXDCXB.json","view_paper":"https://pith.science/paper/VFIS3C2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12447&json=true","fetch_graph":"https://pith.science/api/pith-number/VFIS3C2AH5NBEQAKXEEYTXDCXB/graph.json","fetch_events":"https://pith.science/api/pith-number/VFIS3C2AH5NBEQAKXEEYTXDCXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFIS3C2AH5NBEQAKXEEYTXDCXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFIS3C2AH5NBEQAKXEEYTXDCXB/action/storage_attestation","attest_author":"https://pith.science/pith/VFIS3C2AH5NBEQAKXEEYTXDCXB/action/author_attestation","sign_citation":"https://pith.science/pith/VFIS3C2AH5NBEQAKXEEYTXDCXB/action/citation_signature","submit_replication":"https://pith.science/pith/VFIS3C2AH5NBEQAKXEEYTXDCXB/action/replication_record"}},"created_at":"2026-07-05T08:33:46.442340+00:00","updated_at":"2026-07-05T08:33:46.442340+00:00"}