{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BMH7HSP5TRVB5YIOVMZ3S3MJKM","short_pith_number":"pith:BMH7HSP5","schema_version":"1.0","canonical_sha256":"0b0ff3c9fd9c6a1ee10eab33b96d89530e5949ff822f7961ee2a3be419302ebf","source":{"kind":"arxiv","id":"2412.00055","version":1},"attestation_state":"computed","paper":{"title":"High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ayushi Agarwal, Promila Ghosh, Sourav Banerjee","submitted_at":"2024-11-24T17:02:48Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems in the clinical domain face significant challenges, notably the need to recognise specialised medical vocabulary accurately and meet stringent precision requirements. We introduce United-MedASR, a novel architecture that addresses these challenges by integrating synthetic data generation, precision ASR fine-tuning, and advanced semantic enhancement techniques. United-MedASR constructs a specialised medical vocabulary by synthesising data from authoritative sources such as ICD-10 (International Classification of Diseases, 10th Revision), MIMS (Monthly "},"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":"2412.00055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-24T17:02:48Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"43414884838f7bb9cd92f24d08fea8384904663e63731bacbe067fe910d38fdc","abstract_canon_sha256":"e66ba74f6138796d1c5100ce22af0d065308a480be616c52f0774c8f5a64894b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:35.395941Z","signature_b64":"h43mnTpZmU7+lo48hTEHcqIsW8ZCBiFwOJX7SMEpUkIXX03mn5tXrOrzYladKK8nfW34BG1qpauXDxcnvcTlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b0ff3c9fd9c6a1ee10eab33b96d89530e5949ff822f7961ee2a3be419302ebf","last_reissued_at":"2026-07-05T09:42:35.395424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:35.395424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ayushi Agarwal, Promila Ghosh, Sourav Banerjee","submitted_at":"2024-11-24T17:02:48Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems in the clinical domain face significant challenges, notably the need to recognise specialised medical vocabulary accurately and meet stringent precision requirements. We introduce United-MedASR, a novel architecture that addresses these challenges by integrating synthetic data generation, precision ASR fine-tuning, and advanced semantic enhancement techniques. United-MedASR constructs a specialised medical vocabulary by synthesising data from authoritative sources such as ICD-10 (International Classification of Diseases, 10th Revision), MIMS (Monthly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00055","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/2412.00055/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":"2412.00055","created_at":"2026-07-05T09:42:35.395492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00055v1","created_at":"2026-07-05T09:42:35.395492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00055","created_at":"2026-07-05T09:42:35.395492+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMH7HSP5TRVB","created_at":"2026-07-05T09:42:35.395492+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMH7HSP5TRVB5YIO","created_at":"2026-07-05T09:42:35.395492+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMH7HSP5","created_at":"2026-07-05T09:42:35.395492+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.04638","citing_title":"SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23284","citing_title":"Au-M-ol: A Unified Model for Medical Audio and Language Understanding","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM","json":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM.json","graph_json":"https://pith.science/api/pith-number/BMH7HSP5TRVB5YIOVMZ3S3MJKM/graph.json","events_json":"https://pith.science/api/pith-number/BMH7HSP5TRVB5YIOVMZ3S3MJKM/events.json","paper":"https://pith.science/paper/BMH7HSP5"},"agent_actions":{"view_html":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM","download_json":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM.json","view_paper":"https://pith.science/paper/BMH7HSP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00055&json=true","fetch_graph":"https://pith.science/api/pith-number/BMH7HSP5TRVB5YIOVMZ3S3MJKM/graph.json","fetch_events":"https://pith.science/api/pith-number/BMH7HSP5TRVB5YIOVMZ3S3MJKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM/action/storage_attestation","attest_author":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM/action/author_attestation","sign_citation":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM/action/citation_signature","submit_replication":"https://pith.science/pith/BMH7HSP5TRVB5YIOVMZ3S3MJKM/action/replication_record"}},"created_at":"2026-07-05T09:42:35.395492+00:00","updated_at":"2026-07-05T09:42:35.395492+00:00"}