{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZPBEVIY53E3EUEJODJDDFVXPAW","short_pith_number":"pith:ZPBEVIY5","schema_version":"1.0","canonical_sha256":"cbc24aa31dd9364a112e1a4632d6ef058110a1370f9a58203b6546012a84eb36","source":{"kind":"arxiv","id":"2505.13971","version":2},"attestation_state":"computed","paper":{"title":"The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chin-Hui Lee, Hang Chen, Jingdong Chen, Jun Du, Ming Gao, Odette Scharenborg, Shilong Wu, Shinji Watanabe, Siniscalchi Sabato Marco","submitted_at":"2025-05-20T06:11:51Z","abstract_excerpt":"Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Diarization (AVSD), Audio-Visual Speech Recognition (AVSR), and Audio-Visual Diarization and Recognition (AVDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing s"},"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":"2505.13971","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T06:11:51Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"45bbb25573482080c3dca95c3d22b38667d042ae1b03ca5918d26b89aa774a0b","abstract_canon_sha256":"23ba2d0dd61746b4e9d80690a2f945e1507d8222cb5dea3bc0aa3fcc828bc169"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:08.845672Z","signature_b64":"XKelD9OevTIMbhy+1xBjwtBCyknT1ctaCtzqOvw5Az2p6zd9GbE8asCZJWCyrdc/D/nZcfEUQd/XaN+FtZKYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbc24aa31dd9364a112e1a4632d6ef058110a1370f9a58203b6546012a84eb36","last_reissued_at":"2026-07-05T11:10:08.845152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:08.845152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chin-Hui Lee, Hang Chen, Jingdong Chen, Jun Du, Ming Gao, Odette Scharenborg, Shilong Wu, Shinji Watanabe, Siniscalchi Sabato Marco","submitted_at":"2025-05-20T06:11:51Z","abstract_excerpt":"Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Diarization (AVSD), Audio-Visual Speech Recognition (AVSR), and Audio-Visual Diarization and Recognition (AVDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13971","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/2505.13971/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":"2505.13971","created_at":"2026-07-05T11:10:08.845208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13971v2","created_at":"2026-07-05T11:10:08.845208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13971","created_at":"2026-07-05T11:10:08.845208+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPBEVIY53E3E","created_at":"2026-07-05T11:10:08.845208+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPBEVIY53E3EUEJO","created_at":"2026-07-05T11:10:08.845208+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPBEVIY5","created_at":"2026-07-05T11:10:08.845208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13073","citing_title":"OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22467","citing_title":"DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW","json":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW.json","graph_json":"https://pith.science/api/pith-number/ZPBEVIY53E3EUEJODJDDFVXPAW/graph.json","events_json":"https://pith.science/api/pith-number/ZPBEVIY53E3EUEJODJDDFVXPAW/events.json","paper":"https://pith.science/paper/ZPBEVIY5"},"agent_actions":{"view_html":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW","download_json":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW.json","view_paper":"https://pith.science/paper/ZPBEVIY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13971&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPBEVIY53E3EUEJODJDDFVXPAW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPBEVIY53E3EUEJODJDDFVXPAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/action/storage_attestation","attest_author":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/action/author_attestation","sign_citation":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/action/citation_signature","submit_replication":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/action/replication_record"}},"created_at":"2026-07-05T11:10:08.845208+00:00","updated_at":"2026-07-05T11:10:08.845208+00:00"}