{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EMZ3KFTWOVDAZ7CXP67FUD3UWE","short_pith_number":"pith:EMZ3KFTW","schema_version":"1.0","canonical_sha256":"2333b5167675460cfc577fbe5a0f74b11cae8c01dde532155a868fcc77876459","source":{"kind":"arxiv","id":"2104.04045","version":2},"attestation_state":"computed","paper":{"title":"End-to-end speaker segmentation for overlap-aware resegmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Antoine Laurent, Herv\\'e Bredin","submitted_at":"2021-04-08T20:38:17Z","abstract_excerpt":"Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped speech detection), we propose to train an end-to-end segmentation model that does it directly. Inspired by the original end-to-end neural speaker diarization approach (EEND), the task is modeled as a multi-label classification problem using permutation-invariant training. The main difference is that our model operates on short audio chunks (5 seconds) but at "},"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":"2104.04045","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-08T20:38:17Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"e5e0e5fe413cf01ad19d88ac1d6531d095c82f181b2d52e5b9ea1949c132c592","abstract_canon_sha256":"c1fb8e3da48d95237f0d3ddea2525bc14cfb1efb46acaa870fd8abbe744e8be7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:10.872522Z","signature_b64":"PQYEO41K8aKgGPY5dnGZZFaiGxOS2UP77Z9NMKBd9EyUp+Ztp6MoBaA088C/9GDtUkeYuRxRfMhLndt6/Q/2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2333b5167675460cfc577fbe5a0f74b11cae8c01dde532155a868fcc77876459","last_reissued_at":"2026-07-05T02:48:10.871963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:10.871963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end speaker segmentation for overlap-aware resegmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Antoine Laurent, Herv\\'e Bredin","submitted_at":"2021-04-08T20:38:17Z","abstract_excerpt":"Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped speech detection), we propose to train an end-to-end segmentation model that does it directly. Inspired by the original end-to-end neural speaker diarization approach (EEND), the task is modeled as a multi-label classification problem using permutation-invariant training. The main difference is that our model operates on short audio chunks (5 seconds) but at "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04045","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/2104.04045/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":"2104.04045","created_at":"2026-07-05T02:48:10.872028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04045v2","created_at":"2026-07-05T02:48:10.872028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04045","created_at":"2026-07-05T02:48:10.872028+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMZ3KFTWOVDA","created_at":"2026-07-05T02:48:10.872028+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMZ3KFTWOVDAZ7CX","created_at":"2026-07-05T02:48:10.872028+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMZ3KFTW","created_at":"2026-07-05T02:48:10.872028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08125","citing_title":"PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE","json":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE.json","graph_json":"https://pith.science/api/pith-number/EMZ3KFTWOVDAZ7CXP67FUD3UWE/graph.json","events_json":"https://pith.science/api/pith-number/EMZ3KFTWOVDAZ7CXP67FUD3UWE/events.json","paper":"https://pith.science/paper/EMZ3KFTW"},"agent_actions":{"view_html":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE","download_json":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE.json","view_paper":"https://pith.science/paper/EMZ3KFTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04045&json=true","fetch_graph":"https://pith.science/api/pith-number/EMZ3KFTWOVDAZ7CXP67FUD3UWE/graph.json","fetch_events":"https://pith.science/api/pith-number/EMZ3KFTWOVDAZ7CXP67FUD3UWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE/action/storage_attestation","attest_author":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE/action/author_attestation","sign_citation":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE/action/citation_signature","submit_replication":"https://pith.science/pith/EMZ3KFTWOVDAZ7CXP67FUD3UWE/action/replication_record"}},"created_at":"2026-07-05T02:48:10.872028+00:00","updated_at":"2026-07-05T02:48:10.872028+00:00"}