{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AG7HIORX3PTVRO3VG5EH4WWLXW","short_pith_number":"pith:AG7HIORX","schema_version":"1.0","canonical_sha256":"01be743a37dbe758bb7537487e5acbbd9c8578f58cf0ec93e1eac86023c7de70","source":{"kind":"arxiv","id":"2506.05796","version":1},"attestation_state":"computed","paper":{"title":"Diarization-Aware Multi-Speaker Automatic Speech Recognition via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Beilong Tang, Ming Cheng, Ming Li, Yuke Lin, Ze Li","submitted_at":"2025-06-06T06:43:34Z","abstract_excerpt":"Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training (SOT)-style methods serve as common solutions, they often discard absolute timing information, limiting their utility in time-sensitive scenarios. Leveraging recent advances in large language models (LLMs) for conversational audio processing, we propose a novel diarization-aware multi-speaker ASR system that integrates speaker diarization with LLM-based transc"},"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":"2506.05796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-06T06:43:34Z","cross_cats_sorted":[],"title_canon_sha256":"da86e02bff0d93f3151c6dd7cc96fd9db5f1a631acfafb2b30822b7ec208bd6f","abstract_canon_sha256":"711e1af0ac6e3144961d64a43a2032c4f60cbe935ce5f1101194897a8c5ebe54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:10.095692Z","signature_b64":"u3QEixiUy7/FC3R+B6Da843/kCIZY4WmX2KGGr5muGP7jSfYVJD9TnYwSXL6g6dBj7Hs6RvnrfGKB+weklaSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01be743a37dbe758bb7537487e5acbbd9c8578f58cf0ec93e1eac86023c7de70","last_reissued_at":"2026-07-05T11:17:10.095148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:10.095148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diarization-Aware Multi-Speaker Automatic Speech Recognition via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Beilong Tang, Ming Cheng, Ming Li, Yuke Lin, Ze Li","submitted_at":"2025-06-06T06:43:34Z","abstract_excerpt":"Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training (SOT)-style methods serve as common solutions, they often discard absolute timing information, limiting their utility in time-sensitive scenarios. Leveraging recent advances in large language models (LLMs) for conversational audio processing, we propose a novel diarization-aware multi-speaker ASR system that integrates speaker diarization with LLM-based transc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05796","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/2506.05796/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":"2506.05796","created_at":"2026-07-05T11:17:10.095211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05796v1","created_at":"2026-07-05T11:17:10.095211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05796","created_at":"2026-07-05T11:17:10.095211+00:00"},{"alias_kind":"pith_short_12","alias_value":"AG7HIORX3PTV","created_at":"2026-07-05T11:17:10.095211+00:00"},{"alias_kind":"pith_short_16","alias_value":"AG7HIORX3PTVRO3V","created_at":"2026-07-05T11:17:10.095211+00:00"},{"alias_kind":"pith_short_8","alias_value":"AG7HIORX","created_at":"2026-07-05T11:17:10.095211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10853","citing_title":"Speech Encoder Fusion for LLM-based Automatic Speech Recognition","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22467","citing_title":"DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW","json":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW.json","graph_json":"https://pith.science/api/pith-number/AG7HIORX3PTVRO3VG5EH4WWLXW/graph.json","events_json":"https://pith.science/api/pith-number/AG7HIORX3PTVRO3VG5EH4WWLXW/events.json","paper":"https://pith.science/paper/AG7HIORX"},"agent_actions":{"view_html":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW","download_json":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW.json","view_paper":"https://pith.science/paper/AG7HIORX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05796&json=true","fetch_graph":"https://pith.science/api/pith-number/AG7HIORX3PTVRO3VG5EH4WWLXW/graph.json","fetch_events":"https://pith.science/api/pith-number/AG7HIORX3PTVRO3VG5EH4WWLXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW/action/storage_attestation","attest_author":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW/action/author_attestation","sign_citation":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW/action/citation_signature","submit_replication":"https://pith.science/pith/AG7HIORX3PTVRO3VG5EH4WWLXW/action/replication_record"}},"created_at":"2026-07-05T11:17:10.095211+00:00","updated_at":"2026-07-05T11:17:10.095211+00:00"}