{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFLM6AKG72JOGRM6CBTBCPSNTH","short_pith_number":"pith:XFLM6AKG","schema_version":"1.0","canonical_sha256":"b956cf0146fe92e3459e1066113e4d99e9c4d6d50b6fe3da2dc8bd1feb5c66e1","source":{"kind":"arxiv","id":"2411.14100","version":2},"attestation_state":"computed","paper":{"title":"BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"eess.AS","authors_text":"Anup Singh, Kris Demuynck, Vipul Arora","submitted_at":"2024-11-21T13:05:18Z","abstract_excerpt":"Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that encodes speech into discrete, speaker-agnostic semantic tokens. This facilitates fast retrieval using text-based search algorithms and effectively handles out-of-vocabulary terms. Our approach focuses on generating consistent token sequences across varying utterances of the same term. We also propose a bidirectional state space modeling within the Mamba encoder, t"},"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":"2411.14100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T13:05:18Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"1d6189ae1876a47bfbc836003c608de448d4b43ec989aa963400c82c16e5be22","abstract_canon_sha256":"f78ec772ecb8887c1f1924503921022e628547747b992727cc491afcc67e88a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:07.699004Z","signature_b64":"uKGoJrDIcE0nAX1gx+ThGEFXG+mk6FzTWOcOxuw3RycwLp6uUzW4K5uPPIIeguZlvVGxDBXFUTX22rQ8Wi1TBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b956cf0146fe92e3459e1066113e4d99e9c4d6d50b6fe3da2dc8bd1feb5c66e1","last_reissued_at":"2026-07-05T09:53:07.698534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:07.698534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"eess.AS","authors_text":"Anup Singh, Kris Demuynck, Vipul Arora","submitted_at":"2024-11-21T13:05:18Z","abstract_excerpt":"Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that encodes speech into discrete, speaker-agnostic semantic tokens. This facilitates fast retrieval using text-based search algorithms and effectively handles out-of-vocabulary terms. Our approach focuses on generating consistent token sequences across varying utterances of the same term. We also propose a bidirectional state space modeling within the Mamba encoder, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14100","kind":"arxiv","version":2},"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/2411.14100/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":"2411.14100","created_at":"2026-07-05T09:53:07.698587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14100v2","created_at":"2026-07-05T09:53:07.698587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14100","created_at":"2026-07-05T09:53:07.698587+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFLM6AKG72JO","created_at":"2026-07-05T09:53:07.698587+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFLM6AKG72JOGRM6","created_at":"2026-07-05T09:53:07.698587+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFLM6AKG","created_at":"2026-07-05T09:53:07.698587+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/XFLM6AKG72JOGRM6CBTBCPSNTH","json":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH.json","graph_json":"https://pith.science/api/pith-number/XFLM6AKG72JOGRM6CBTBCPSNTH/graph.json","events_json":"https://pith.science/api/pith-number/XFLM6AKG72JOGRM6CBTBCPSNTH/events.json","paper":"https://pith.science/paper/XFLM6AKG"},"agent_actions":{"view_html":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH","download_json":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH.json","view_paper":"https://pith.science/paper/XFLM6AKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14100&json=true","fetch_graph":"https://pith.science/api/pith-number/XFLM6AKG72JOGRM6CBTBCPSNTH/graph.json","fetch_events":"https://pith.science/api/pith-number/XFLM6AKG72JOGRM6CBTBCPSNTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/action/storage_attestation","attest_author":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/action/author_attestation","sign_citation":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/action/citation_signature","submit_replication":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/action/replication_record"}},"created_at":"2026-07-05T09:53:07.698587+00:00","updated_at":"2026-07-05T09:53:07.698587+00:00"}