{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NY6QCASUU57AR76M2ZWDQ3LQSZ","short_pith_number":"pith:NY6QCASU","schema_version":"1.0","canonical_sha256":"6e3d010254a77e08ffccd66c386d709657274ae8fe3d60dfb8c23e82f6d621e2","source":{"kind":"arxiv","id":"2301.06056","version":1},"attestation_state":"computed","paper":{"title":"Improving Noise Robustness for Spoken Content Retrieval using Semi-supervised ASR and N-best Transcripts for BERT-based Ranking Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gareth. J. F. Jones, Yasufumi Moriya","submitted_at":"2023-01-15T09:52:07Z","abstract_excerpt":"BERT-based re-ranking and dense retrieval (DR) systems have been shown to improve search effectiveness for spoken content retrieval (SCR). However, both methods can still show a reduction in effectiveness when using ASR transcripts in comparison to accurate manual transcripts. We find that a known-item search task on the How2 dataset of spoken instruction videos shows a reduction in mean reciprocal rank (MRR) scores of 10-14%. As a potential method to reduce this disparity, we investigate the use of semi-supervised ASR transcripts and N-best ASR transcripts to mitigate ASR errors for spoken se"},"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":"2301.06056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-01-15T09:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"b322f0da3670ceb1d55eb3b25054068a71346afb287f20265ad486f4a6af86af","abstract_canon_sha256":"f6b7f30858fa944ae059a2d94f4edacb051f60267da87551a6f8ae8e6e4e984f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:27.370089Z","signature_b64":"HH6yKJeNM+IgDR8IZUWsvKEHPHrKJZC+sF9dz2UJtn4v6LjuTheyA9uVZc/faC9yMLQrxEVKmVjriqym4duUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e3d010254a77e08ffccd66c386d709657274ae8fe3d60dfb8c23e82f6d621e2","last_reissued_at":"2026-07-05T05:33:27.369643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:27.369643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Noise Robustness for Spoken Content Retrieval using Semi-supervised ASR and N-best Transcripts for BERT-based Ranking Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gareth. J. F. Jones, Yasufumi Moriya","submitted_at":"2023-01-15T09:52:07Z","abstract_excerpt":"BERT-based re-ranking and dense retrieval (DR) systems have been shown to improve search effectiveness for spoken content retrieval (SCR). However, both methods can still show a reduction in effectiveness when using ASR transcripts in comparison to accurate manual transcripts. We find that a known-item search task on the How2 dataset of spoken instruction videos shows a reduction in mean reciprocal rank (MRR) scores of 10-14%. As a potential method to reduce this disparity, we investigate the use of semi-supervised ASR transcripts and N-best ASR transcripts to mitigate ASR errors for spoken se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06056","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/2301.06056/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":"2301.06056","created_at":"2026-07-05T05:33:27.369695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06056v1","created_at":"2026-07-05T05:33:27.369695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06056","created_at":"2026-07-05T05:33:27.369695+00:00"},{"alias_kind":"pith_short_12","alias_value":"NY6QCASUU57A","created_at":"2026-07-05T05:33:27.369695+00:00"},{"alias_kind":"pith_short_16","alias_value":"NY6QCASUU57AR76M","created_at":"2026-07-05T05:33:27.369695+00:00"},{"alias_kind":"pith_short_8","alias_value":"NY6QCASU","created_at":"2026-07-05T05:33:27.369695+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/NY6QCASUU57AR76M2ZWDQ3LQSZ","json":"https://pith.science/pith/NY6QCASUU57AR76M2ZWDQ3LQSZ.json","graph_json":"https://pith.science/api/pith-number/NY6QCASUU57AR76M2ZWDQ3LQSZ/graph.json","events_json":"https://pith.science/api/pith-number/NY6QCASUU57AR76M2ZWDQ3LQSZ/events.json","paper":"https://pith.science/paper/NY6QCASU"},"agent_actions":{"view_html":"https://pith.science/pith/NY6QCASUU57AR76M2ZWDQ3LQSZ","download_json":"https://pith.science/pith/NY6QCASUU57AR76M2ZWDQ3LQSZ.json","view_paper":"https://pith.science/paper/NY6QCASU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06056&json=true","fetch_graph":"https://pith.science/api/pith-number/NY6QCASUU57AR76M2ZWDQ3LQSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NY6QCASUU57AR76M2ZWDQ3LQSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NY6QCASUU57AR76M2ZWDQ3LQSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NY6QCASUU57AR76M2ZWDQ3LQSZ/action/storage_attestation","attest_author":"https://pith.science/pith/NY6QCASUU57AR76M2ZWDQ3LQSZ/action/author_attestation","sign_citation":"https://pith.science/pith/NY6QCASUU57AR76M2ZWDQ3LQSZ/action/citation_signature","submit_replication":"https://pith.science/pith/NY6QCASUU57AR76M2ZWDQ3LQSZ/action/replication_record"}},"created_at":"2026-07-05T05:33:27.369695+00:00","updated_at":"2026-07-05T05:33:27.369695+00:00"}