{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FY43KKPKEIHXIS5MOVDBB27XR4","short_pith_number":"pith:FY43KKPK","schema_version":"1.0","canonical_sha256":"2e39b529ea220f744bac754610ebf78f260814b33e5603cb738d90232d9af364","source":{"kind":"arxiv","id":"2305.12459","version":1},"attestation_state":"computed","paper":{"title":"CASA-ASR: Context-Aware Speaker-Attributed ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fan Yu, Jie Zhang, Li-Rong Dai, Mohan Shi, Qian Chen, Shiliang Zhang, Yangze Li, Zhihao Du","submitted_at":"2023-05-21T13:32:19Z","abstract_excerpt":"Recently, speaker-attributed automatic speech recognition (SA-ASR) has attracted a wide attention, which aims at answering the question ``who spoke what''. Different from modular systems, end-to-end (E2E) SA-ASR minimizes the speaker-dependent recognition errors directly and shows a promising applicability. In this paper, we propose a context-aware SA-ASR (CASA-ASR) model by enhancing the contextual modeling ability of E2E SA-ASR. Specifically, in CASA-ASR, a contextual text encoder is involved to aggregate the semantic information of the whole utterance, and a context-dependent scorer is empl"},"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":"2305.12459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T13:32:19Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"e50fb401c2b473af989ad9f203afb90e63899a0b069e2e75c73767faa2bca70c","abstract_canon_sha256":"e8f08a92a6bf084c93fac54cc0a0e2f227905972cd58607088de381881a911e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:10.895781Z","signature_b64":"Np9YCQMkWFPrG36wlJRpdlCOLGjaEhhadGjsfnpC5Io+QZmB7ndcRBLkAMUZBY1LvWolLDjyLFBVNUI8EXfTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e39b529ea220f744bac754610ebf78f260814b33e5603cb738d90232d9af364","last_reissued_at":"2026-07-05T06:12:10.895326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:10.895326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CASA-ASR: Context-Aware Speaker-Attributed ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fan Yu, Jie Zhang, Li-Rong Dai, Mohan Shi, Qian Chen, Shiliang Zhang, Yangze Li, Zhihao Du","submitted_at":"2023-05-21T13:32:19Z","abstract_excerpt":"Recently, speaker-attributed automatic speech recognition (SA-ASR) has attracted a wide attention, which aims at answering the question ``who spoke what''. Different from modular systems, end-to-end (E2E) SA-ASR minimizes the speaker-dependent recognition errors directly and shows a promising applicability. In this paper, we propose a context-aware SA-ASR (CASA-ASR) model by enhancing the contextual modeling ability of E2E SA-ASR. Specifically, in CASA-ASR, a contextual text encoder is involved to aggregate the semantic information of the whole utterance, and a context-dependent scorer is empl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12459","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/2305.12459/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":"2305.12459","created_at":"2026-07-05T06:12:10.895387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12459v1","created_at":"2026-07-05T06:12:10.895387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12459","created_at":"2026-07-05T06:12:10.895387+00:00"},{"alias_kind":"pith_short_12","alias_value":"FY43KKPKEIHX","created_at":"2026-07-05T06:12:10.895387+00:00"},{"alias_kind":"pith_short_16","alias_value":"FY43KKPKEIHXIS5M","created_at":"2026-07-05T06:12:10.895387+00:00"},{"alias_kind":"pith_short_8","alias_value":"FY43KKPK","created_at":"2026-07-05T06:12:10.895387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10456","citing_title":"Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4","json":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4.json","graph_json":"https://pith.science/api/pith-number/FY43KKPKEIHXIS5MOVDBB27XR4/graph.json","events_json":"https://pith.science/api/pith-number/FY43KKPKEIHXIS5MOVDBB27XR4/events.json","paper":"https://pith.science/paper/FY43KKPK"},"agent_actions":{"view_html":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4","download_json":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4.json","view_paper":"https://pith.science/paper/FY43KKPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12459&json=true","fetch_graph":"https://pith.science/api/pith-number/FY43KKPKEIHXIS5MOVDBB27XR4/graph.json","fetch_events":"https://pith.science/api/pith-number/FY43KKPKEIHXIS5MOVDBB27XR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4/action/storage_attestation","attest_author":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4/action/author_attestation","sign_citation":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4/action/citation_signature","submit_replication":"https://pith.science/pith/FY43KKPKEIHXIS5MOVDBB27XR4/action/replication_record"}},"created_at":"2026-07-05T06:12:10.895387+00:00","updated_at":"2026-07-05T06:12:10.895387+00:00"}