{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NTPNFXFW4XJKDTBDN46VQBZAHQ","short_pith_number":"pith:NTPNFXFW","schema_version":"1.0","canonical_sha256":"6cded2dcb6e5d2a1cc236f3d5807203c03cde0b7e0ef2bf2401365c9564d05f6","source":{"kind":"arxiv","id":"2601.17640","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Anfeng Xu, Catherine Lord, Shrikanth Narayanan, Somer Bishop, Tiantian Feng","submitted_at":"2026-01-25T01:00:41Z","abstract_excerpt":"Accurate transcription and speaker role diarization of child-adult spoken interactions are crucial for developmental and clinical research. However, manual annotation is time-consuming and challenging to scale. Existing automated systems typically rely on cascaded speaker diarization and automatic speech recognition pipelines, which can lead to error propagation. This paper presents a unified end-to-end framework that extends the Whisper encoder-decoder architecture to jointly model ASR and child-adult speaker role diarization. The proposed approach integrates: (i) a serialized output training"},"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":"2601.17640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-25T01:00:41Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4ab934f8f0b116ff00f49f789f5bbfd2624bef69383d4c4cd75407ea51cab429","abstract_canon_sha256":"d68f80c15112d20b1a3aee2fa08f95e8116defce65ec819a038f875ec0ef0e69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:18:46.883796Z","signature_b64":"GhJHtbYju3J8jYjwJKEp/Ptz2/uuEhPd8wRbBZHGGvTPZ5MtsqcuOHeSApJBczfDeSo4tp1YGCVHnKmRXhA/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cded2dcb6e5d2a1cc236f3d5807203c03cde0b7e0ef2bf2401365c9564d05f6","last_reissued_at":"2026-08-11T02:18:46.882133Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:18:46.882133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Anfeng Xu, Catherine Lord, Shrikanth Narayanan, Somer Bishop, Tiantian Feng","submitted_at":"2026-01-25T01:00:41Z","abstract_excerpt":"Accurate transcription and speaker role diarization of child-adult spoken interactions are crucial for developmental and clinical research. However, manual annotation is time-consuming and challenging to scale. Existing automated systems typically rely on cascaded speaker diarization and automatic speech recognition pipelines, which can lead to error propagation. This paper presents a unified end-to-end framework that extends the Whisper encoder-decoder architecture to jointly model ASR and child-adult speaker role diarization. The proposed approach integrates: (i) a serialized output training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.17640","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/2601.17640/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":"2601.17640","created_at":"2026-08-11T02:18:46.882792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.17640v2","created_at":"2026-08-11T02:18:46.882792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17640","created_at":"2026-08-11T02:18:46.882792+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTPNFXFW4XJK","created_at":"2026-08-11T02:18:46.882792+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTPNFXFW4XJKDTBD","created_at":"2026-08-11T02:18:46.882792+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTPNFXFW","created_at":"2026-08-11T02:18:46.882792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.05201","citing_title":"Exploring Speech Foundation Models for Speaker Diarization Across Lifespan","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05201","citing_title":"Exploring Speech Foundation Models for Speaker Diarization Across Lifespan","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ","json":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ.json","graph_json":"https://pith.science/api/pith-number/NTPNFXFW4XJKDTBDN46VQBZAHQ/graph.json","events_json":"https://pith.science/api/pith-number/NTPNFXFW4XJKDTBDN46VQBZAHQ/events.json","paper":"https://pith.science/paper/NTPNFXFW"},"agent_actions":{"view_html":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ","download_json":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ.json","view_paper":"https://pith.science/paper/NTPNFXFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.17640&json=true","fetch_graph":"https://pith.science/api/pith-number/NTPNFXFW4XJKDTBDN46VQBZAHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NTPNFXFW4XJKDTBDN46VQBZAHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ/action/storage_attestation","attest_author":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ/action/author_attestation","sign_citation":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ/action/citation_signature","submit_replication":"https://pith.science/pith/NTPNFXFW4XJKDTBDN46VQBZAHQ/action/replication_record"}},"created_at":"2026-08-11T02:18:46.882792+00:00","updated_at":"2026-08-11T02:18:46.882792+00:00"}