{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LJN3FVKF7J6YI3UOW6RVZIWKE2","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":"4c1aa394909e13678948bc99733f5827202b27f0a64e1c47b389ab7c145bc352","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-14T21:24:56Z","title_canon_sha256":"3f8a599f32ecf51edfd792ba475dac6be2fe392c7e929c2ffc906bc845681280"},"schema_version":"1.0","source":{"id":"2005.07272","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07272","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07272v2","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07272","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"LJN3FVKF7J6Y","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_16","alias_value":"LJN3FVKF7J6YI3UO","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_8","alias_value":"LJN3FVKF","created_at":"2026-07-05T01:48:09Z"}],"graph_snapshots":[{"event_id":"sha256:c8358fc376528bf2fdbff6382c3c6310589ab296e449e981f3a667435a4a5eb2","target":"graph","created_at":"2026-07-05T01:48:09Z","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/2005.07272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker diarization for real-life scenarios is an extremely challenging problem. Widely used clustering-based diarization approaches perform rather poorly in such conditions, mainly due to the limited ability to handle overlapping speech. We propose a novel Target-Speaker Voice Activity Detection (TS-VAD) approach, which directly predicts an activity of each speaker on each time frame. TS-VAD model takes conventional speech features (e.g., MFCC) along with i-vectors for each speaker as inputs. A set of binary classification output layers produces activities of each speaker. I-vectors can be es","authors_text":"Aleksandr Laptev, Aleksei Romanenko, Andrei Andrusenko, Anton Mitrofanov, Ivan Medennikov, Ivan Podluzhny, Ivan Sorokin, Mariya Korenevskaya, Maxim Korenevsky, Tatiana Prisyach, Tatiana Timofeeva, Yuri Khokhlov","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-14T21:24:56Z","title":"Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07272","kind":"arxiv","version":2},"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":"sha256:113bee4a7c83c4e947cd9920b0c260d0388eb7c1ee1a9a6b87e9e250ab2e60a3","target":"record","created_at":"2026-07-05T01:48:09Z","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":"4c1aa394909e13678948bc99733f5827202b27f0a64e1c47b389ab7c145bc352","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-14T21:24:56Z","title_canon_sha256":"3f8a599f32ecf51edfd792ba475dac6be2fe392c7e929c2ffc906bc845681280"},"schema_version":"1.0","source":{"id":"2005.07272","kind":"arxiv","version":2}},"canonical_sha256":"5a5bb2d545fa7d846e8eb7a35ca2ca26b4f754789d2135e39e36dfc7e4bf0184","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a5bb2d545fa7d846e8eb7a35ca2ca26b4f754789d2135e39e36dfc7e4bf0184","first_computed_at":"2026-07-05T01:48:09.542322Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:09.542322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rzKkfbfiS1z/mKF+E4HAMmC7oSMyrQGw0y2e1YUgPmsYVqeRSeZ8DNcc3ZM2GQC/B8cBeLTzykl59aPMyEMPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:09.542873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.07272","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:113bee4a7c83c4e947cd9920b0c260d0388eb7c1ee1a9a6b87e9e250ab2e60a3","sha256:c8358fc376528bf2fdbff6382c3c6310589ab296e449e981f3a667435a4a5eb2"],"state_sha256":"adf231da15bc0013c2895672037155c77680ecacae68726e72fa47eef1e2fdf7"}