{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EF5G2XVKUHRMMBLUT36YC5ZNFT","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":"3e0d3ac28e0a2f2baf509170813b31b7978c36bfd70e76c5868bfbdb822f1dd2","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","title_canon_sha256":"b7558eea0cf9ae93f41a3825186295ecc1631b4f2ef87cbc209490cac89d2159"},"schema_version":"1.0","source":{"id":"2409.04859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04859","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04859v2","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04859","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"EF5G2XVKUHRM","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"EF5G2XVKUHRMMBLU","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"EF5G2XVK","created_at":"2026-07-05T09:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:e24decf959d067fe6e603b956da38858afe8a058ad2f12aec982ea06de39afb7","target":"graph","created_at":"2026-07-05T09:09:06Z","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/2409.04859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, w","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Yidi Jiang, Zhengyang Chen","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","title":"Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04859","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":"sha256:20120980d5b1821652e746ca4ddab038683aaa73883bd1b4b8f20e351a59bdc3","target":"record","created_at":"2026-07-05T09:09:06Z","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":"3e0d3ac28e0a2f2baf509170813b31b7978c36bfd70e76c5868bfbdb822f1dd2","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","title_canon_sha256":"b7558eea0cf9ae93f41a3825186295ecc1631b4f2ef87cbc209490cac89d2159"},"schema_version":"1.0","source":{"id":"2409.04859","kind":"arxiv","version":2}},"canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","first_computed_at":"2026-07-05T09:09:06.504959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:06.504959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ee1KFSm0Z1SsTLAQgTgap6su1R1BefN3rY6hCfmwrYkppBHW/3Fd2r4TLZx1Rda3jt89h2wJwI8IQiUB+V7xBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:06.505440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20120980d5b1821652e746ca4ddab038683aaa73883bd1b4b8f20e351a59bdc3","sha256:e24decf959d067fe6e603b956da38858afe8a058ad2f12aec982ea06de39afb7"],"state_sha256":"665cca593b09297a064538362b67473eee5afce5bea2efd06e248856ed0a7a34"}