{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LASCAYAJPHPQKKUC5TXM47XKUE","short_pith_number":"pith:LASCAYAJ","schema_version":"1.0","canonical_sha256":"582420600979df052a82eceece7eeaa10123065ba7c83e08340bd611a1cf0e9f","source":{"kind":"arxiv","id":"2406.04927","version":3},"attestation_state":"computed","paper":{"title":"LLM-based speaker diarization correction: A generalizable approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Anzar Abbas, Georgios Efstathiadis, Vijay Yadav","submitted_at":"2024-06-07T13:33:22Z","abstract_excerpt":"Speaker diarization is necessary for interpreting conversations transcribed using automated speech recognition (ASR) tools. Despite significant developments in diarization methods, diarization accuracy remains an issue. Here, we investigate the use of large language models (LLMs) for diarization correction as a post-processing step. LLMs were fine-tuned using the Fisher corpus, a large dataset of transcribed conversations. The ability of the models to improve diarization accuracy in a holdout dataset from the Fisher corpus as well as an independent dataset was measured. We report that fine-tun"},"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":"2406.04927","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T13:33:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a155861779d18d335c97fe7d614f4a98430ce4ea26c3f5b2cf13250e9ea36358","abstract_canon_sha256":"5047640cfa7b3b71f85a18d01ab77762cd3ae1db134a1d9ac8cc0dda2c5c304a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:27.339938Z","signature_b64":"6dmnFDry0WpVu3MMtJi7rxz0HGQF/eYsnqUGzmkEYHtqVRGJH+NUJGLk745+NM7+nW1u/E8IaHxB0CWeQPyeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"582420600979df052a82eceece7eeaa10123065ba7c83e08340bd611a1cf0e9f","last_reissued_at":"2026-07-05T10:32:27.339057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:27.339057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-based speaker diarization correction: A generalizable approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Anzar Abbas, Georgios Efstathiadis, Vijay Yadav","submitted_at":"2024-06-07T13:33:22Z","abstract_excerpt":"Speaker diarization is necessary for interpreting conversations transcribed using automated speech recognition (ASR) tools. Despite significant developments in diarization methods, diarization accuracy remains an issue. Here, we investigate the use of large language models (LLMs) for diarization correction as a post-processing step. LLMs were fine-tuned using the Fisher corpus, a large dataset of transcribed conversations. The ability of the models to improve diarization accuracy in a holdout dataset from the Fisher corpus as well as an independent dataset was measured. We report that fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04927","kind":"arxiv","version":3},"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/2406.04927/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":"2406.04927","created_at":"2026-07-05T10:32:27.339175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04927v3","created_at":"2026-07-05T10:32:27.339175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04927","created_at":"2026-07-05T10:32:27.339175+00:00"},{"alias_kind":"pith_short_12","alias_value":"LASCAYAJPHPQ","created_at":"2026-07-05T10:32:27.339175+00:00"},{"alias_kind":"pith_short_16","alias_value":"LASCAYAJPHPQKKUC","created_at":"2026-07-05T10:32:27.339175+00:00"},{"alias_kind":"pith_short_8","alias_value":"LASCAYAJ","created_at":"2026-07-05T10:32:27.339175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.00086","citing_title":"Iterative LLM-based improvement for French Clinical Interview Transcription and Speaker Diarization","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE","json":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE.json","graph_json":"https://pith.science/api/pith-number/LASCAYAJPHPQKKUC5TXM47XKUE/graph.json","events_json":"https://pith.science/api/pith-number/LASCAYAJPHPQKKUC5TXM47XKUE/events.json","paper":"https://pith.science/paper/LASCAYAJ"},"agent_actions":{"view_html":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE","download_json":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE.json","view_paper":"https://pith.science/paper/LASCAYAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04927&json=true","fetch_graph":"https://pith.science/api/pith-number/LASCAYAJPHPQKKUC5TXM47XKUE/graph.json","fetch_events":"https://pith.science/api/pith-number/LASCAYAJPHPQKKUC5TXM47XKUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/action/storage_attestation","attest_author":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/action/author_attestation","sign_citation":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/action/citation_signature","submit_replication":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/action/replication_record"}},"created_at":"2026-07-05T10:32:27.339175+00:00","updated_at":"2026-07-05T10:32:27.339175+00:00"}