{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VFIS3C2AH5NBEQAKXEEYTXDCXB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f7b7ed7b225b87dcf92e8fb3752c36a8e8961a14407c9c489eaca107de06a551","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T09:48:59Z","title_canon_sha256":"aab2f2cd07a3c09745053e6c426ac4b3a496b82a7ff8decce14720a0605f0503"},"schema_version":"1.0","source":{"id":"2406.12447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12447","created_at":"2026-07-05T08:33:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12447v1","created_at":"2026-07-05T08:33:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12447","created_at":"2026-07-05T08:33:46Z"},{"alias_kind":"pith_short_12","alias_value":"VFIS3C2AH5NB","created_at":"2026-07-05T08:33:46Z"},{"alias_kind":"pith_short_16","alias_value":"VFIS3C2AH5NBEQAK","created_at":"2026-07-05T08:33:46Z"},{"alias_kind":"pith_short_8","alias_value":"VFIS3C2A","created_at":"2026-07-05T08:33:46Z"}],"graph_snapshots":[{"event_id":"sha256:7de2338519bbf7ee83b9921d95f1023ebdcbe17f5d199373a68a2ec93a70a6e1","target":"graph","created_at":"2026-07-05T08:33:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.12447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baochen Yang, Hao Li, Haoyu Li, Kai Yu, Linfeng Yu, Tian Tan, Yu Xi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T09:48:59Z","title":"Text-aware Speech Separation for Multi-talker Keyword Spotting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12447","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:37e996a4c64bd980a359cc09d0ca92fe999c12f30ab61818996bad6b7dbbb582","target":"record","created_at":"2026-07-05T08:33:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f7b7ed7b225b87dcf92e8fb3752c36a8e8961a14407c9c489eaca107de06a551","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T09:48:59Z","title_canon_sha256":"aab2f2cd07a3c09745053e6c426ac4b3a496b82a7ff8decce14720a0605f0503"},"schema_version":"1.0","source":{"id":"2406.12447","kind":"arxiv","version":1}},"canonical_sha256":"a9512d8b403f5a12400ab90989dc62b848098228643b1e468734e5dceb5f1a7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9512d8b403f5a12400ab90989dc62b848098228643b1e468734e5dceb5f1a7a","first_computed_at":"2026-07-05T08:33:46.442275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:46.442275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qlwdF5bHvuOeMg+AsUvMMJ7+Ybj/+GppEstfJLqgcAxBnhm+Z5PDaSKtLi3nlj5o6u15wk1G3WyK/aimOO7vAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:46.442696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37e996a4c64bd980a359cc09d0ca92fe999c12f30ab61818996bad6b7dbbb582","sha256:7de2338519bbf7ee83b9921d95f1023ebdcbe17f5d199373a68a2ec93a70a6e1"],"state_sha256":"2feda3105c32249cbbc7a2dee4090640f7e32fc4b574b8435e9d5a85a8dd970a"}