{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NTLHLSYAKRORSZ77S5NWSOJZCG","short_pith_number":"pith:NTLHLSYA","schema_version":"1.0","canonical_sha256":"6cd675cb00545d1967ff975b693939119ff271e0696c53231350336183975fea","source":{"kind":"arxiv","id":"1812.07209","version":2},"attestation_state":"computed","paper":{"title":"Constrained speaker diarization of TV series based on visual patterns","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.MM","authors_text":"Georges Linares (LIA), Xavier Bost (LIA)","submitted_at":"2018-12-18T07:29:27Z","abstract_excerpt":"Speaker diarization, usually denoted as the ''who spoke when'' task, turns out to be particularly challenging when applied to fictional films, where many characters talk in various acoustic conditions (background music, sound effects...). Despite this acoustic variability , such movies exhibit specific visual patterns in the dialogue scenes. In this paper, we introduce a two-step method to achieve speaker diarization in TV series: a speaker diarization is first performed locally in the scenes detected as dialogues; then, the hypothesized local speakers are merged in a second agglomerative clus"},"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":"1812.07209","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-12-18T07:29:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4fa529acc5765646a8295b40838970fa4a8af1fe445c514efb722071723aa06b","abstract_canon_sha256":"9a311a60c7384d6717199ff709e8dce602e173dae6bcc02f1430410334810c5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:12.401862Z","signature_b64":"ikj/wqhWF31kcAsoI4mVrvBjBd8hwPFRFQIfa4/qc6zSxeogPNz+O+Pm/W9ymL+PZpp93oYqP+FQ9q4wU3/cDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cd675cb00545d1967ff975b693939119ff271e0696c53231350336183975fea","last_reissued_at":"2026-05-17T23:48:12.400270Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:12.400270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained speaker diarization of TV series based on visual patterns","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.MM","authors_text":"Georges Linares (LIA), Xavier Bost (LIA)","submitted_at":"2018-12-18T07:29:27Z","abstract_excerpt":"Speaker diarization, usually denoted as the ''who spoke when'' task, turns out to be particularly challenging when applied to fictional films, where many characters talk in various acoustic conditions (background music, sound effects...). Despite this acoustic variability , such movies exhibit specific visual patterns in the dialogue scenes. In this paper, we introduce a two-step method to achieve speaker diarization in TV series: a speaker diarization is first performed locally in the scenes detected as dialogues; then, the hypothesized local speakers are merged in a second agglomerative clus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07209","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":"1812.07209","created_at":"2026-05-17T23:48:12.401170+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07209v2","created_at":"2026-05-17T23:48:12.401170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07209","created_at":"2026-05-17T23:48:12.401170+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTLHLSYAKROR","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTLHLSYAKRORSZ77","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTLHLSYA","created_at":"2026-05-18T12:32:40.477152+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/NTLHLSYAKRORSZ77S5NWSOJZCG","json":"https://pith.science/pith/NTLHLSYAKRORSZ77S5NWSOJZCG.json","graph_json":"https://pith.science/api/pith-number/NTLHLSYAKRORSZ77S5NWSOJZCG/graph.json","events_json":"https://pith.science/api/pith-number/NTLHLSYAKRORSZ77S5NWSOJZCG/events.json","paper":"https://pith.science/paper/NTLHLSYA"},"agent_actions":{"view_html":"https://pith.science/pith/NTLHLSYAKRORSZ77S5NWSOJZCG","download_json":"https://pith.science/pith/NTLHLSYAKRORSZ77S5NWSOJZCG.json","view_paper":"https://pith.science/paper/NTLHLSYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07209&json=true","fetch_graph":"https://pith.science/api/pith-number/NTLHLSYAKRORSZ77S5NWSOJZCG/graph.json","fetch_events":"https://pith.science/api/pith-number/NTLHLSYAKRORSZ77S5NWSOJZCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTLHLSYAKRORSZ77S5NWSOJZCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTLHLSYAKRORSZ77S5NWSOJZCG/action/storage_attestation","attest_author":"https://pith.science/pith/NTLHLSYAKRORSZ77S5NWSOJZCG/action/author_attestation","sign_citation":"https://pith.science/pith/NTLHLSYAKRORSZ77S5NWSOJZCG/action/citation_signature","submit_replication":"https://pith.science/pith/NTLHLSYAKRORSZ77S5NWSOJZCG/action/replication_record"}},"created_at":"2026-05-17T23:48:12.401170+00:00","updated_at":"2026-05-17T23:48:12.401170+00:00"}