{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NZUQ3AT54BKIE2CKM4WVQ5E6FF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f176ce0cd79603d5ba0bf25d9b8bd10cd9037e24478db6ff7e17951e4b368fbb","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-04-13T17:16:56Z","title_canon_sha256":"62d08ac7b2fdf868a17a934d70b3c0de11589634d74265f71a8a868372d13005"},"schema_version":"1.0","source":{"id":"2004.06756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.06756","created_at":"2026-07-05T00:55:21Z"},{"alias_kind":"arxiv_version","alias_value":"2004.06756v1","created_at":"2026-07-05T00:55:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06756","created_at":"2026-07-05T00:55:21Z"},{"alias_kind":"pith_short_12","alias_value":"NZUQ3AT54BKI","created_at":"2026-07-05T00:55:21Z"},{"alias_kind":"pith_short_16","alias_value":"NZUQ3AT54BKIE2CK","created_at":"2026-07-05T00:55:21Z"},{"alias_kind":"pith_short_8","alias_value":"NZUQ3AT5","created_at":"2026-07-05T00:55:21Z"}],"graph_snapshots":[{"event_id":"sha256:395922e47a9cd26b91f09ab1191efa87c457a03da427777608656dc83796ee65","target":"graph","created_at":"2026-07-05T00:55:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.06756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents a novel approach for speaker diarization to leverage lexical information provided by automatic speech recognition. We propose a speaker diarization system that can incorporate word-level speaker turn probabilities with speaker embeddings into a speaker clustering process to improve the overall diarization accuracy. To integrate lexical and acoustic information in a comprehensive way during clustering, we introduce an adjacency matrix integration for spectral clustering. Since words and word boundary information for word-level speaker turn probability estimation are provided ","authors_text":"Bowen Zhou, Jing Huang, Kyu J. Han, Panayiotis Georgiou, Shrikanth Narayanan, Tae Jin Park, Xiaodong He","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-04-13T17:16:56Z","title":"Speaker Diarization with Lexical Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06756","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1b79da0707f74d3c33f2f9689cb6cfca8cd9d47ea5cce54c032ed48ff2f87d37","target":"record","created_at":"2026-07-05T00:55:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f176ce0cd79603d5ba0bf25d9b8bd10cd9037e24478db6ff7e17951e4b368fbb","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-04-13T17:16:56Z","title_canon_sha256":"62d08ac7b2fdf868a17a934d70b3c0de11589634d74265f71a8a868372d13005"},"schema_version":"1.0","source":{"id":"2004.06756","kind":"arxiv","version":1}},"canonical_sha256":"6e690d827de05482684a672d58749e294fd638ca7a88c4a433df0721b017a95d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e690d827de05482684a672d58749e294fd638ca7a88c4a433df0721b017a95d","first_computed_at":"2026-07-05T00:55:21.631193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:55:21.631193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E7YcH2y9hxxa38sk5RsiU8CJX4L/cbBtXR42vBaT5uF2DIeNfHtUHY6HG6wDmNvaFJRr7ELpDStlNVYk4NiUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:55:21.631642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.06756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b79da0707f74d3c33f2f9689cb6cfca8cd9d47ea5cce54c032ed48ff2f87d37","sha256:395922e47a9cd26b91f09ab1191efa87c457a03da427777608656dc83796ee65"],"state_sha256":"0b892804fc5ab51a102a1ced31b78c28753bf7528d5aac3b47e637c2444f354d"}