{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DTHZNXHM72CXU2HEEQMYSFNMUF","short_pith_number":"pith:DTHZNXHM","schema_version":"1.0","canonical_sha256":"1ccf96dcecfe857a68e424198915aca1700e27f8cf21ce0153d34cef399d4489","source":{"kind":"arxiv","id":"2506.01916","version":1},"attestation_state":"computed","paper":{"title":"DNCASR: End-to-End Training for Speaker-Attributed ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chao Zhang, Philip C. Woodland, Xianrui Zheng","submitted_at":"2025-06-02T17:36:57Z","abstract_excerpt":"This paper introduces DNCASR, a novel end-to-end trainable system designed for joint neural speaker clustering and automatic speech recognition (ASR), enabling speaker-attributed transcription of long multi-party meetings. DNCASR uses two separate encoders to independently encode global speaker characteristics and local waveform information, along with two linked decoders to generate speaker-attributed transcriptions. The use of linked decoders allows the entire system to be jointly trained under a unified loss function. By employing a serialised training approach, DNCASR effectively addresses"},"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":"2506.01916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T17:36:57Z","cross_cats_sorted":[],"title_canon_sha256":"bb4f0ab849c64fb32ee61ffe62a5259b9a7d23ae6f634a0d8ff9adc700cad76a","abstract_canon_sha256":"112f800c4be3c4ca0c22bee510227727b78a8880248de849d176be58c23d213e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:21.317600Z","signature_b64":"ZYX/3P6C3IvHIPssAnMI1K2cISAdu0gfXFK3W6LC/3rNKLYg7EeYfjdgT0KdS2Mnllk6dC+tZi8MfSXR6gItAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ccf96dcecfe857a68e424198915aca1700e27f8cf21ce0153d34cef399d4489","last_reissued_at":"2026-07-05T11:14:21.317168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:21.317168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DNCASR: End-to-End Training for Speaker-Attributed ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chao Zhang, Philip C. Woodland, Xianrui Zheng","submitted_at":"2025-06-02T17:36:57Z","abstract_excerpt":"This paper introduces DNCASR, a novel end-to-end trainable system designed for joint neural speaker clustering and automatic speech recognition (ASR), enabling speaker-attributed transcription of long multi-party meetings. DNCASR uses two separate encoders to independently encode global speaker characteristics and local waveform information, along with two linked decoders to generate speaker-attributed transcriptions. The use of linked decoders allows the entire system to be jointly trained under a unified loss function. By employing a serialised training approach, DNCASR effectively addresses"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01916","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/2506.01916/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":"2506.01916","created_at":"2026-07-05T11:14:21.317222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01916v1","created_at":"2026-07-05T11:14:21.317222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01916","created_at":"2026-07-05T11:14:21.317222+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTHZNXHM72CX","created_at":"2026-07-05T11:14:21.317222+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTHZNXHM72CXU2HE","created_at":"2026-07-05T11:14:21.317222+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTHZNXHM","created_at":"2026-07-05T11:14:21.317222+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/DTHZNXHM72CXU2HEEQMYSFNMUF","json":"https://pith.science/pith/DTHZNXHM72CXU2HEEQMYSFNMUF.json","graph_json":"https://pith.science/api/pith-number/DTHZNXHM72CXU2HEEQMYSFNMUF/graph.json","events_json":"https://pith.science/api/pith-number/DTHZNXHM72CXU2HEEQMYSFNMUF/events.json","paper":"https://pith.science/paper/DTHZNXHM"},"agent_actions":{"view_html":"https://pith.science/pith/DTHZNXHM72CXU2HEEQMYSFNMUF","download_json":"https://pith.science/pith/DTHZNXHM72CXU2HEEQMYSFNMUF.json","view_paper":"https://pith.science/paper/DTHZNXHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01916&json=true","fetch_graph":"https://pith.science/api/pith-number/DTHZNXHM72CXU2HEEQMYSFNMUF/graph.json","fetch_events":"https://pith.science/api/pith-number/DTHZNXHM72CXU2HEEQMYSFNMUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTHZNXHM72CXU2HEEQMYSFNMUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTHZNXHM72CXU2HEEQMYSFNMUF/action/storage_attestation","attest_author":"https://pith.science/pith/DTHZNXHM72CXU2HEEQMYSFNMUF/action/author_attestation","sign_citation":"https://pith.science/pith/DTHZNXHM72CXU2HEEQMYSFNMUF/action/citation_signature","submit_replication":"https://pith.science/pith/DTHZNXHM72CXU2HEEQMYSFNMUF/action/replication_record"}},"created_at":"2026-07-05T11:14:21.317222+00:00","updated_at":"2026-07-05T11:14:21.317222+00:00"}