{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GK5O3NIN4CUAB453BQLI2DWOYD","short_pith_number":"pith:GK5O3NIN","schema_version":"1.0","canonical_sha256":"32baedb50de0a800f3bb0c168d0ecec0db532ca5a731b59f7a3ff2e10c2ff953","source":{"kind":"arxiv","id":"1812.07205","version":2},"attestation_state":"computed","paper":{"title":"Audiovisual speaker diarization of TV series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.MM","authors_text":"Georges Linar\\`es (LIA), Serigne Gueye (LIA), Xavier Bost (LIA)","submitted_at":"2018-12-18T07:21:36Z","abstract_excerpt":"Speaker diarization may be difficult to achieve when applied to narrative films, where speakers usually talk in adverse acoustic conditions: background music, sound effects, wide variations in intonation may hide the inter-speaker variability and make audio-based speaker diarization approaches error prone. On the other hand, such fictional movies exhibit strong regularities at the image level, particularly within dialogue scenes. In this paper, we propose to perform speaker diarization within dialogue scenes of TV series by combining the audio and video modalities: speaker diarization is first"},"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":"1812.07205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-12-18T07:21:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1ef957cf0c780cff97d4bdba95e91aee123e1f5c99970687d870a8df6a2736fa","abstract_canon_sha256":"b888b8bdbe829026513d8a49c08538f654aad6baae57d2e1ee1eb7fb0ad1e01d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:14.589347Z","signature_b64":"9kPMKqdvYADIm+n+ONAkZ78XNO23pRmwcfQAby/L5s7jKk6M6R2Pv7aNxRP/V0Hjb/NkqZ0je8AhG9OBzdyRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32baedb50de0a800f3bb0c168d0ecec0db532ca5a731b59f7a3ff2e10c2ff953","last_reissued_at":"2026-05-17T23:57:14.588804Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:14.588804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audiovisual speaker diarization of TV series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.MM","authors_text":"Georges Linar\\`es (LIA), Serigne Gueye (LIA), Xavier Bost (LIA)","submitted_at":"2018-12-18T07:21:36Z","abstract_excerpt":"Speaker diarization may be difficult to achieve when applied to narrative films, where speakers usually talk in adverse acoustic conditions: background music, sound effects, wide variations in intonation may hide the inter-speaker variability and make audio-based speaker diarization approaches error prone. On the other hand, such fictional movies exhibit strong regularities at the image level, particularly within dialogue scenes. In this paper, we propose to perform speaker diarization within dialogue scenes of TV series by combining the audio and video modalities: speaker diarization is first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07205","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":""},"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":"1812.07205","created_at":"2026-05-17T23:57:14.588900+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07205v2","created_at":"2026-05-17T23:57:14.588900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07205","created_at":"2026-05-17T23:57:14.588900+00:00"},{"alias_kind":"pith_short_12","alias_value":"GK5O3NIN4CUA","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GK5O3NIN4CUAB453","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GK5O3NIN","created_at":"2026-05-18T12:32:25.280505+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/GK5O3NIN4CUAB453BQLI2DWOYD","json":"https://pith.science/pith/GK5O3NIN4CUAB453BQLI2DWOYD.json","graph_json":"https://pith.science/api/pith-number/GK5O3NIN4CUAB453BQLI2DWOYD/graph.json","events_json":"https://pith.science/api/pith-number/GK5O3NIN4CUAB453BQLI2DWOYD/events.json","paper":"https://pith.science/paper/GK5O3NIN"},"agent_actions":{"view_html":"https://pith.science/pith/GK5O3NIN4CUAB453BQLI2DWOYD","download_json":"https://pith.science/pith/GK5O3NIN4CUAB453BQLI2DWOYD.json","view_paper":"https://pith.science/paper/GK5O3NIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07205&json=true","fetch_graph":"https://pith.science/api/pith-number/GK5O3NIN4CUAB453BQLI2DWOYD/graph.json","fetch_events":"https://pith.science/api/pith-number/GK5O3NIN4CUAB453BQLI2DWOYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GK5O3NIN4CUAB453BQLI2DWOYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GK5O3NIN4CUAB453BQLI2DWOYD/action/storage_attestation","attest_author":"https://pith.science/pith/GK5O3NIN4CUAB453BQLI2DWOYD/action/author_attestation","sign_citation":"https://pith.science/pith/GK5O3NIN4CUAB453BQLI2DWOYD/action/citation_signature","submit_replication":"https://pith.science/pith/GK5O3NIN4CUAB453BQLI2DWOYD/action/replication_record"}},"created_at":"2026-05-17T23:57:14.588900+00:00","updated_at":"2026-05-17T23:57:14.588900+00:00"}